ARC-AGI-2
ARC-AGI-2 results that Epoch AI republishes from the original runner.
No filters. Showing 299 of 299 rows.
1 OpenAIDossier | max | No harness | GPT-6 Astra, Score: 95% (scale 0.0 to 100.0)95% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
2 GoogleDossier | medium | No harness | Gemini 4 Carbon, Score: 94.2% (scale 0.0 to 100.0)94.2% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
2 OpenAIDossier | max | No harness | GPT-6.1 Sol, Score: 94.2% (scale 0.0 to 100.0)94.2% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
4 AnthropicDossier | xhigh | No harness | Fable 5.2, Score: 93.8% (scale 0.0 to 100.0)93.8% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
5 OpenAIDossier | xhigh | No harness | GPT-6 Astra, Score: 93.3% (scale 0.0 to 100.0)93.3% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
5 AnthropicDossier | high | No harness | Opus 5.5, Score: 93.3% (scale 0.0 to 100.0)93.3% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
7 AnthropicDossier | max | No harness | Fable 5.2, Score: 92.5% (scale 0.0 to 100.0)92.5% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
7 OpenAIDossier | max | No harness | GPT-5.6 Sol, Score: 92.5% (scale 0.0 to 100.0)92.5% | $1.44 | Runs unstated | Cost kind unknown | Date not stated |
7 AnthropicDossier | xhigh | No harness | Opus 5.5, Score: 92.5% (scale 0.0 to 100.0)92.5% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
10 GoogleDossier | high | No harness | Gemini 4 Carbon, Score: 92.1% (scale 0.0 to 100.0)92.1% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
10 OpenAIDossier | high | No harness | GPT-6 Astra, Score: 92.1% (scale 0.0 to 100.0)92.1% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
10 OpenAIDossier | medium | No harness | GPT-6 Astra, Score: 92.1% (scale 0.0 to 100.0)92.1% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
13 OpenAIDossier | xhigh | No harness | GPT-6.1 Sol, Score: 91.7% (scale 0.0 to 100.0)91.7% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
13 OpenAIDossier | high | No harness | GPT-6.1 Sol, Score: 91.7% (scale 0.0 to 100.0)91.7% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
13 AnthropicDossier | max | No harness | Opus 5.5, Score: 91.7% (scale 0.0 to 100.0)91.7% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
16 GoogleDossier | high | No harness | Gemini 4 Argon, Score: 91.3% (scale 0.0 to 100.0)91.3% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
17 AnthropicDossier | max | No harness | Opus 5, Score: 90.4% (scale 0.0 to 100.0)90.4% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
18 AnthropicDossier | high | No harness | Fable 5.2, Score: 90.4% (scale 0.0 to 100.0)90.4% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
19 AnthropicDossier | max | No harness | Fable 5.1, Score: 90% (scale 0.0 to 100.0)90% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
19 AnthropicDossier | xhigh | No harness | Fable 5.1, Score: 90% (scale 0.0 to 100.0)90% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
19 OpenAIDossier | xhigh | No harness | GPT-5.6 Sol, Score: 90% (scale 0.0 to 100.0)90% | $1.04 | Runs unstated | Cost kind unknown | Date not stated |
19 OpenAIDossier | xhigh | No harness | GPT-5.6 Sol, Score: 90% (scale 0.0 to 100.0)90% | Not tested | Runs unstated | Cost kind unknown | Date not stated |
- 1OpenAIDossier
max
Score
GPT-6 Astra, Score: 95% (scale 0.0 to 100.0)95%- Cost per task
- Not tested
- 2GoogleDossier
medium
Score
Gemini 4 Carbon, Score: 94.2% (scale 0.0 to 100.0)94.2%- Cost per task
- Not tested
- 2OpenAIDossier
max
Score
GPT-6.1 Sol, Score: 94.2% (scale 0.0 to 100.0)94.2%- Cost per task
- Not tested
- 4AnthropicDossier
xhigh
Score
Fable 5.2, Score: 93.8% (scale 0.0 to 100.0)93.8%- Cost per task
- Not tested
- 5OpenAIDossier
xhigh
Score
GPT-6 Astra, Score: 93.3% (scale 0.0 to 100.0)93.3%- Cost per task
- Not tested
- 5AnthropicDossier
high
Score
Opus 5.5, Score: 93.3% (scale 0.0 to 100.0)93.3%- Cost per task
- Not tested
- 7AnthropicDossier
max
Score
Fable 5.2, Score: 92.5% (scale 0.0 to 100.0)92.5%- Cost per task
- Not tested
- 7OpenAIDossier
max
Score
GPT-5.6 Sol, Score: 92.5% (scale 0.0 to 100.0)92.5%- Cost per task
- $1.44
- 7AnthropicDossier
xhigh
Score
Opus 5.5, Score: 92.5% (scale 0.0 to 100.0)92.5%- Cost per task
- Not tested
- 10GoogleDossier
high
Score
Gemini 4 Carbon, Score: 92.1% (scale 0.0 to 100.0)92.1%- Cost per task
- Not tested
- 10OpenAIDossier
high
Score
GPT-6 Astra, Score: 92.1% (scale 0.0 to 100.0)92.1%- Cost per task
- Not tested
- 10OpenAIDossier
medium
Score
GPT-6 Astra, Score: 92.1% (scale 0.0 to 100.0)92.1%- Cost per task
- Not tested
- 13OpenAIDossier
xhigh
Score
GPT-6.1 Sol, Score: 91.7% (scale 0.0 to 100.0)91.7%- Cost per task
- Not tested
- 13OpenAIDossier
high
Score
GPT-6.1 Sol, Score: 91.7% (scale 0.0 to 100.0)91.7%- Cost per task
- Not tested
- 13AnthropicDossier
max
Score
Opus 5.5, Score: 91.7% (scale 0.0 to 100.0)91.7%- Cost per task
- Not tested
- 16GoogleDossier
high
Score
Gemini 4 Argon, Score: 91.3% (scale 0.0 to 100.0)91.3%- Cost per task
- Not tested
- 17AnthropicDossier
max
Score
Opus 5, Score: 90.4% (scale 0.0 to 100.0)90.4%- Cost per task
- Not tested
- 18AnthropicDossier
high
Score
Fable 5.2, Score: 90.4% (scale 0.0 to 100.0)90.4%- Cost per task
- Not tested
- 19AnthropicDossier
max
Score
Fable 5.1, Score: 90% (scale 0.0 to 100.0)90%- Cost per task
- Not tested
- 19AnthropicDossier
xhigh
Score
Fable 5.1, Score: 90% (scale 0.0 to 100.0)90%- Cost per task
- Not tested
- 19OpenAIDossier
xhigh
Score
GPT-5.6 Sol, Score: 90% (scale 0.0 to 100.0)90%- Cost per task
- $1.04
- 19OpenAIDossier
xhigh
Score
GPT-5.6 Sol, Score: 90% (scale 0.0 to 100.0)90%- Cost per task
- Not tested
- 23AnthropicDossier
medium
Score
Fable 5.2, Score: 89.6% (scale 0.0 to 100.0)89.6%- Cost per task
- Not tested
- 23OpenAIDossier
max
Score
GPT-6 Sol, Score: 89.6% (scale 0.0 to 100.0)89.6%- Cost per task
- Not tested
- 25AnthropicDossier
max
Score
Fable 5, Score: 89.2% (scale 0.0 to 100.0)89.2%- Cost per task
- Not tested
- 25GoogleDossier
high
Score
Gemini 3.8 Flash, Score: 89.2% (scale 0.0 to 100.0)89.2%- Cost per task
- Not tested
- 27AnthropicDossier
high
Score
Fable 5.1, Score: 88.8% (scale 0.0 to 100.0)88.8%- Cost per task
- Not tested
- 28AnthropicDossier
xhigh
Score
Fable 5, Score: 88.3% (scale 0.0 to 100.0)88.3%- Cost per task
- Not tested
- 29AnthropicDossier
max
Score
Opus 5, Score: 88.3% (scale 0.0 to 100.0)88.3%- Cost per task
- Not tested
- 29AnthropicDossier
high
Score
Opus 5, Score: 88.3% (scale 0.0 to 100.0)88.3%- Cost per task
- Not tested
- 31AnthropicDossier
high
Score
Fable 5, Score: 87.5% (scale 0.0 to 100.0)87.5%- Cost per task
- Not tested
- 31AnthropicDossier
medium
Score
Opus 5.5, Score: 87.5% (scale 0.0 to 100.0)87.5%- Cost per task
- Not tested
- 33GoogleDossier
medium
Score
Gemini 4 Argon, Score: 87.1% (scale 0.0 to 100.0)87.1%- Cost per task
- Not tested
- 34AnthropicDossier
low
Score
Fable 5.2, Score: 86.7% (scale 0.0 to 100.0)86.7%- Cost per task
- Not tested
- 34OpenAIDossier
medium
Score
GPT-6.1 Sol, Score: 86.7% (scale 0.0 to 100.0)86.7%- Cost per task
- Not tested
- 36AnthropicDossier
medium
Score
Fable 5.1, Score: 86.3% (scale 0.0 to 100.0)86.3%- Cost per task
- Not tested
- 37OpenAIDossier
high
Score
GPT-5.6 Sol, Score: 85.4% (scale 0.0 to 100.0)85.4%- Cost per task
- $0.74
- 38OpenAIDossier
low
Score
GPT-6 Astra, Score: 85.4% (scale 0.0 to 100.0)85.4%- Cost per task
- Not tested
- 39OpenAIDossier
xhigh
Score
GPT-5.5, Score: 85% (scale 0.0 to 100.0)85%- Cost per task
- $1.87
- 39OpenAIDossier
xhigh
Score
GPT-5.5, Score: 85% (scale 0.0 to 100.0)85%- Cost per task
- Not tested
- 41GoogleDossier
high
Score
Gemini 3.7 Flash, Score: 84.6% (scale 0.0 to 100.0)84.6%- Cost per task
- Not tested
- 42GoogleDossier
Score
Gemini 3 Deep Think Preview, Score: 84.6% (scale 0.0 to 100.0)84.6%- Cost per task
- Not tested
- 42OpenAIDossier
high
Score
GPT-5.5 Pro, Score: 84.6% (scale 0.0 to 100.0)84.6%- Cost per task
- $10.51
- 44OpenAIDossier
xhigh
Score
GPT-5.5 Pro, Score: 84.2% (scale 0.0 to 100.0)84.2%- Cost per task
- $10.76
- 44OpenAIDossier
xhigh
Score
GPT-5.5 Pro, Score: 84.2% (scale 0.0 to 100.0)84.2%- Cost per task
- Not tested
- 46OpenAIDossier
max
Score
GPT-5.6 Terra, Score: 83.9% (scale 0.0 to 100.0)83.9%- Cost per task
- $1.09
- 47AnthropicDossier
xhigh
Score
Sonnet 5.5, Score: 83.9% (scale 0.0 to 100.0)83.9%- Cost per task
- Not tested
- 48OpenAIDossier
xhigh
Score
GPT-5.4 Pro, Score: 83.3% (scale 0.0 to 100.0)83.3%- Cost per task
- $16.41
- 48OpenAIDossier
xhigh
Score
GPT-5.4 Pro, Score: 83.3% (scale 0.0 to 100.0)83.3%- Cost per task
- Not tested
- 48OpenAIDossier
high
Score
GPT-5.5, Score: 83.3% (scale 0.0 to 100.0)83.3%- Cost per task
- $1.45
- 51GoogleDossier
medium
Score
Gemini 3.8 Flash, Score: 82.9% (scale 0.0 to 100.0)82.9%- Cost per task
- Not tested
- 52AnthropicDossier
medium
Score
Fable 5, Score: 82.5% (scale 0.0 to 100.0)82.5%- Cost per task
- Not tested
- 53Thinking MachinesDossier
xhigh
Score
Inkling 2 Small, Score: 81.7% (scale 0.0 to 100.0)81.7%- Cost per task
- Not tested
- 54AnthropicDossier
low
Score
Fable 5.1, Score: 78.3% (scale 0.0 to 100.0)78.3%- Cost per task
- Not tested
- 55DeepSeekDossier
max
Score
DeepSeek V4.1 Flash 1017, Score: 78.1% (scale 0.0 to 100.0)78.1%- Cost per task
- Not tested
- 55OpenAIDossier
xhigh
Score
GPT-6 Sol, Score: 78.1% (scale 0.0 to 100.0)78.1%- Cost per task
- Not tested
- 57GoogleDossier
low
Score
Gemini 3.8 Flash, Score: 77.5% (scale 0.0 to 100.0)77.5%- Cost per task
- Not tested
- 58GoogleDossier
Score
Gemini 3.1 Pro Preview, Score: 77.1% (scale 0.0 to 100.0)77.1%- Cost per task
- $0.96
- 59GoogleDossier
Score
Gemini 3.1 Pro Preview, Score: 77.1% (scale 0.0 to 100.0)77.1%- Cost per task
- $0.96
- 60AnthropicDossier
low
Score
Fable 5, Score: 76.8% (scale 0.0 to 100.0)76.8%- Cost per task
- Not tested
- 61OpenAIDossier
low
Score
GPT-6.1 Sol, Score: 76.7% (scale 0.0 to 100.0)76.7%- Cost per task
- Not tested
- 62AnthropicDossier
max
Score
Opus 4.7, Score: 75.8% (scale 0.0 to 100.0)75.8%- Cost per task
- Not tested
- 63AnthropicDossier
max
Score
Opus 4.7, Score: 75.8% (scale 0.0 to 100.0)75.8%- Cost per task
- $7.43
- 64OpenAIDossier
xhigh
Score
GPT-5.6 Terra, Score: 74.2% (scale 0.0 to 100.0)74.2%- Cost per task
- $0.69
- 64OpenAIDossier
xhigh
Score
GPT-5.6 Terra, Score: 74.2% (scale 0.0 to 100.0)74.2%- Cost per task
- Not tested
- 66OpenAIDossier
xhigh
Score
GPT-5.4, Score: 74% (scale 0.0 to 100.0)74%- Cost per task
- $1.52
- 66OpenAIDossier
xhigh
Score
GPT-5.4, Score: 74% (scale 0.0 to 100.0)74%- Cost per task
- Not tested
- 68DeepSeekDossier
low
Score
DeepSeek V4.1 Flash 1017, Score: 73.6% (scale 0.0 to 100.0)73.6%- Cost per task
- Not tested
- 69DeepSeekDossier
max
Score
DeepSeek V4.1 Flash, Score: 72.9% (scale 0.0 to 100.0)72.9%- Cost per task
- Not tested
- 70GoogleDossier
high
Score
Gemini 3.5 Flash, Score: 72.1% (scale 0.0 to 100.0)72.1%- Cost per task
- $0.85
- 70AnthropicDossier
high
Score
Opus 4.8, Score: 72.1% (scale 0.0 to 100.0)72.1%- Cost per task
- $2.74
- 72AnthropicDossier
medium
Score
Opus 4.8, Score: 71.7% (scale 0.0 to 100.0)71.7%- Cost per task
- $2.39
- 73OpenAIDossier
medium
Score
GPT-5.5, Score: 70.4% (scale 0.0 to 100.0)70.4%- Cost per task
- $0.86
- 74AnthropicDossier
low
Score
Opus 5.5, Score: 70.1% (scale 0.0 to 100.0)70.1%- Cost per task
- Not tested
- 75AnthropicDossier
high · 120,000 budget
Score
Opus 4.6, Score: 69.2% (scale 0.0 to 100.0)69.2%- Cost per task
- Not tested
- 76OpenAIDossier
high
Score
GPT-6 Sol, Score: 68.9% (scale 0.0 to 100.0)68.9%- Cost per task
- Not tested
- 77AnthropicDossier
max · 120,000 budget
Score
Opus 4.6, Score: 68.8% (scale 0.0 to 100.0)68.8%- Cost per task
- Not tested
- 78DeepSeekDossier
high
Score
DeepSeek V4.1 Flash 1017, Score: 68.6% (scale 0.0 to 100.0)68.6%- Cost per task
- Not tested
- 79AnthropicDossier
high
Score
Opus 4.7, Score: 68.3% (scale 0.0 to 100.0)68.3%- Cost per task
- Not tested
- 80AnthropicDossier
high
Score
Opus 4.7, Score: 68.3% (scale 0.0 to 100.0)68.3%- Cost per task
- $3.17
- 81DeepSeekDossier
high
Score
DeepSeek V4.1 Flash, Score: 67.5% (scale 0.0 to 100.0)67.5%- Cost per task
- Not tested
- 81OpenAIDossier
high
Score
GPT-5.4, Score: 67.5% (scale 0.0 to 100.0)67.5%- Cost per task
- $1.02
- 81AnthropicDossier
medium
Score
Opus 4.7, Score: 67.5% (scale 0.0 to 100.0)67.5%- Cost per task
- $2.96
- 84AnthropicDossier
high
Score
Sonnet 5.5, Score: 67.4% (scale 0.0 to 100.0)67.4%- Cost per task
- Not tested
- 85xAIDossier
xhigh
Score
Grok 4.6, Score: 67.1% (scale 0.0 to 100.0)67.1%- Cost per task
- Not tested
- 86OpenAIDossier
medium
Score
GPT-5.6 Sol, Score: 67.1% (scale 0.0 to 100.0)67.1%- Cost per task
- $0.47
- 86OpenAIDossier
high
Score
GPT-5.6 Terra, Score: 67.1% (scale 0.0 to 100.0)67.1%- Cost per task
- $0.55
- 88AnthropicDossier
medium · 120,000 budget
Score
Opus 4.6, Score: 66.3% (scale 0.0 to 100.0)66.3%- Cost per task
- Not tested
- 89Z.aiDossier
max
Score
GLM-5.3 Flash, Score: 65.8% (scale 0.0 to 100.0)65.8%- Cost per task
- Not tested
- 90xAIDossier
Score
Grok 4.20, Score: 65.1% (scale 0.0 to 100.0)65.1%- Cost per task
- $0.92
- 91xAIDossier
high
Score
Grok 4.6, Score: 65.1% (scale 0.0 to 100.0)65.1%- Cost per task
- Not tested
- 92AnthropicDossier
low · 120,000 budget
Score
Opus 4.6, Score: 64.6% (scale 0.0 to 100.0)64.6%- Cost per task
- Not tested
- 93GoogleDossier
medium
Score
Gemini 3.7 Flash, Score: 63.8% (scale 0.0 to 100.0)63.8%- Cost per task
- Not tested
- 94AnthropicDossier
low
Score
Opus 4.8, Score: 62.2% (scale 0.0 to 100.0)62.2%- Cost per task
- $1.68
- 95AnthropicDossier
low
Score
Opus 4.7, Score: 62.1% (scale 0.0 to 100.0)62.1%- Cost per task
- $2.38
- 96DeepSeekDossier
max
Score
DeepSeek V4-Flash 0731, Score: 61.4% (scale 0.0 to 100.0)61.4%- Cost per task
- Not tested
- 96xAIDossier
xhigh
Score
Grok 4.7, Score: 61.4% (scale 0.0 to 100.0)61.4%- Cost per task
- Not tested
- 98DeepSeekDossier
max
Score
DeepSeek V4 Pro 0813, Score: 61.3% (scale 0.0 to 100.0)61.3%- Cost per task
- Not tested
- 98xAIDossier
medium
Score
Grok 4.6, Score: 61.3% (scale 0.0 to 100.0)61.3%- Cost per task
- Not tested
- 98AnthropicDossier
xhigh
Score
Haiku 5.5, Score: 61.3% (scale 0.0 to 100.0)61.3%- Cost per task
- Not tested
- 101DeepSeekDossier
low
Score
DeepSeek V4.1 Flash, Score: 60.6% (scale 0.0 to 100.0)60.6%- Cost per task
- Not tested
- 102AnthropicDossier
high
Score
Sonnet 4.6, Score: 60.4% (scale 0.0 to 100.0)60.4%- Cost per task
- $2.70
- 103GoogleDossier
high
Score
Gemini 3.6 Flash, Score: 60.4% (scale 0.0 to 100.0)60.4%- Cost per task
- Not tested
- 103Moonshot AIDossier
max
Score
Kimi K3, Score: 60.4% (scale 0.0 to 100.0)60.4%- Cost per task
- $1.59
- 105DeepSeekDossier
high
Score
DeepSeek V4 Pro 0813, Score: 59.7% (scale 0.0 to 100.0)59.7%- Cost per task
- Not tested
- 106OpenAIDossier
none
Score
GPT-6 Astra, Score: 59.6% (scale 0.0 to 100.0)59.6%- Cost per task
- Not tested
- 107OpenAIDossier
max
Score
GPT-5.6 Luna, Score: 59.5% (scale 0.0 to 100.0)59.5%- Cost per task
- $0.67
- 108OpenAIDossier
max
Score
GPT-6 Luna, Score: 59.3% (scale 0.0 to 100.0)59.3%- Cost per task
- Not tested
- 109xAIDossier
medium
Score
Grok 4.7, Score: 58.8% (scale 0.0 to 100.0)58.8%- Cost per task
- Not tested
- 110xAIDossier
high
Score
Grok 4.7, Score: 58.3% (scale 0.0 to 100.0)58.3%- Cost per task
- Not tested
- 111AnthropicDossier
max
Score
Sonnet 4.6, Score: 58.3% (scale 0.0 to 100.0)58.3%- Cost per task
- $2.72
- 112OpenAIDossier
medium
Score
GPT-6 Sol, Score: 57.8% (scale 0.0 to 100.0)57.8%- Cost per task
- Not tested
- 113MetaDossier
xhigh
Score
Muse Spark Open, Score: 57.5% (scale 0.0 to 100.0)57.5%- Cost per task
- Not tested
- 114DeepSeekDossier
low
Score
DeepSeek V4 Pro 0813, Score: 56.3% (scale 0.0 to 100.0)56.3%- Cost per task
- Not tested
- 115DeepSeekDossier
high
Score
DeepSeek V4-Flash 0731, Score: 56% (scale 0.0 to 100.0)56%- Cost per task
- Not tested
- 116OpenAIDossier
medium
Score
GPT-5.4, Score: 55.4% (scale 0.0 to 100.0)55.4%- Cost per task
- $0.68
- 117Moonshot AIDossier
high
Score
Kimi K3, Score: 55% (scale 0.0 to 100.0)55%- Cost per task
- $0.95
- 118OpenAIDossier
high
Score
GPT-5.2 Pro, Score: 54.2% (scale 0.0 to 100.0)54.2%- Cost per task
- $15.72
- 119GoogleDossier
low
Score
Gemini 3.7 Flash, Score: 52.9% (scale 0.0 to 100.0)52.9%- Cost per task
- Not tested
- 120OpenAIDossier
xhigh
Score
GPT-5.2, Score: 52.9% (scale 0.0 to 100.0)52.9%- Cost per task
- $1.90
- 120OpenAIDossier
xhigh
Score
GPT-5.2, Score: 52.9% (scale 0.0 to 100.0)52.9%- Cost per task
- Not tested
- 120OpenAIDossier
xhigh
Score
GPT-5.2, Score: 52.9% (scale 0.0 to 100.0)52.9%- Cost per task
- Not tested
- 123xAIDossier
high
Score
Grok 4.5, Score: 52.6% (scale 0.0 to 100.0)52.6%- Cost per task
- $0.78
- 123xAIDossier
medium
Score
Grok 4.5, Score: 52.6% (scale 0.0 to 100.0)52.6%- Cost per task
- $0.75
- 125GoogleDossier
medium
Score
Gemini 3.6 Flash, Score: 50.4% (scale 0.0 to 100.0)50.4%- Cost per task
- Not tested
- 126Z.aiDossier
high
Score
GLM-5.3 Flash, Score: 50.1% (scale 0.0 to 100.0)50.1%- Cost per task
- Not tested
- 127GoogleDossier
low
Score
Gemini 4 Carbon, Score: 49.6% (scale 0.0 to 100.0)49.6%- Cost per task
- Not tested
- 128OpenAIDossier
xhigh
Score
GPT-5.6 Luna, Score: 47.6% (scale 0.0 to 100.0)47.6%- Cost per task
- $0.54
- 128OpenAIDossier
xhigh
Score
GPT-5.6 Luna, Score: 47.6% (scale 0.0 to 100.0)47.6%- Cost per task
- Not tested
- 130MetaDossier
high
Score
Muse Spark Open, Score: 47.5% (scale 0.0 to 100.0)47.5%- Cost per task
- Not tested
- 131DeepSeekDossier
low
Score
DeepSeek V4-Flash 0731, Score: 46% (scale 0.0 to 100.0)46%- Cost per task
- Not tested
- 132GoogleDossier
Score
Gemini 3 Deep Think Preview, Score: 45.1% (scale 0.0 to 100.0)45.1%- Cost per task
- Not tested
- 133OpenAIDossier
high
Score
GPT-5.2, Score: 43.3% (scale 0.0 to 100.0)43.3%- Cost per task
- $1.39
- 134OpenAIDossier
low
Score
GPT-5.6 Sol, Score: 42.5% (scale 0.0 to 100.0)42.5%- Cost per task
- $0.32
- 135AlibabaDossier
xhigh
Score
Qwen3.8-27B, Score: 42.4% (scale 0.0 to 100.0)42.4%- Cost per task
- Not tested
- 136GoogleDossier
low
Score
Gemini 4 Argon, Score: 42.1% (scale 0.0 to 100.0)42.1%- Cost per task
- Not tested
- 137OpenAIDossier
xhigh
Score
GPT-6 Luna, Score: 41.9% (scale 0.0 to 100.0)41.9%- Cost per task
- Not tested
- 138Thinking MachinesDossier
xhigh
Score
Inkling Small, Score: 40.1% (scale 0.0 to 100.0)40.1%- Cost per task
- Not tested
- 139OpenAIDossier
medium
Score
GPT-5.2 Pro, Score: 38.5% (scale 0.0 to 100.0)38.5%- Cost per task
- $8.99
- 140AnthropicDossier
thinking · 64,000 budget
Score
Opus 4.5, Score: 37.6% (scale 0.0 to 100.0)37.6%- Cost per task
- $2.40
- 141OpenAIDossier
medium
Score
GPT-5.6 Terra, Score: 37.5% (scale 0.0 to 100.0)37.5%- Cost per task
- $0.27
- 142Thinking MachinesDossier
Score
Inkling, Score: 36.5% (scale 0.0 to 100.0)36.5%- Cost per task
- $0.64
- 143GoogleDossier
high
Score
Gemini 3 Flash Preview, Score: 33.6% (scale 0.0 to 100.0)33.6%- Cost per task
- Not tested
- 144OpenAIDossier
low
Score
GPT-5.5, Score: 33.3% (scale 0.0 to 100.0)33.3%- Cost per task
- $0.35
- 145xAIDossier
low
Score
Grok 4.5, Score: 33.1% (scale 0.0 to 100.0)33.1%- Cost per task
- $0.40
- 146Thinking MachinesDossier
high
Score
Inkling Small, Score: 33.1% (scale 0.0 to 100.0)33.1%- Cost per task
- Not tested
- 147AnthropicDossier
medium
Score
Sonnet 5.5, Score: 32.8% (scale 0.0 to 100.0)32.8%- Cost per task
- Not tested
- 148OpenAIDossier
low
Score
GPT-6 Sol, Score: 31.5% (scale 0.0 to 100.0)31.5%- Cost per task
- Not tested
- 149OpenAIDossier
high
Score
GPT-6 Luna, Score: 31.4% (scale 0.0 to 100.0)31.4%- Cost per task
- Not tested
- 150GoogleDossier
Score
Gemini 3 Pro Preview, Score: 31.1% (scale 0.0 to 100.0)31.1%- Cost per task
- Not tested
- 151AnthropicDossier
high
Score
Haiku 5.5, Score: 30.7% (scale 0.0 to 100.0)30.7%- Cost per task
- Not tested
- 152GoogleDossier
low
Score
Gemini 3.6 Flash, Score: 30.4% (scale 0.0 to 100.0)30.4%- Cost per task
- Not tested
- 153OpenAIDossier
high
Score
GPT-5.6 Luna, Score: 29.3% (scale 0.0 to 100.0)29.3%- Cost per task
- $0.29
- 154OpenAIDossier
low
Score
GPT-5.4, Score: 29.2% (scale 0.0 to 100.0)29.2%- Cost per task
- $0.27
- 155Z.aiDossier
low
Score
GLM-5.3 Flash, Score: 27.9% (scale 0.0 to 100.0)27.9%- Cost per task
- Not tested
- 156xAIDossier
low
Score
Grok 4.6, Score: 27.6% (scale 0.0 to 100.0)27.6%- Cost per task
- Not tested
- 157MetaDossier
medium
Score
Muse Spark Open, Score: 27.5% (scale 0.0 to 100.0)27.5%- Cost per task
- Not tested
- 158OpenAIDossier
medium
Score
GPT-5.2, Score: 26.7% (scale 0.0 to 100.0)26.7%- Cost per task
- $0.76
- 159AnthropicDossier
low
Score
Sonnet 5.5, Score: 24% (scale 0.0 to 100.0)24%- Cost per task
- Not tested
- 160ReflectionDossier
xhigh
Score
Beam 1.0, Score: 23.5% (scale 0.0 to 100.0)23.5%- Cost per task
- Not tested
- 161AnthropicDossier
thinking · 16,000 budget
Score
Opus 4.5, Score: 22.8% (scale 0.0 to 100.0)22.8%- Cost per task
- $0.79
- 162AlibabaDossier
low
Score
Qwen3.8-27B, Score: 22.8% (scale 0.0 to 100.0)22.8%- Cost per task
- Not tested
- 163Z.aiDossier
Score
GLM-5.2, Score: 22.8% (scale 0.0 to 100.0)22.8%- Cost per task
- $0.25
- 164ReflectionDossier
high
Score
Beam 1.0, Score: 20% (scale 0.0 to 100.0)20%- Cost per task
- Not tested
- 165OpenAIDossier
xhigh
Score
GPT-5.4 mini, Score: 18.9% (scale 0.0 to 100.0)18.9%- Cost per task
- $0.75
- 165OpenAIDossier
xhigh
Score
GPT-5.4 mini, Score: 18.9% (scale 0.0 to 100.0)18.9%- Cost per task
- Not tested
- 167OpenAIDossier
low
Score
GPT-5.6 Terra, Score: 18.8% (scale 0.0 to 100.0)18.8%- Cost per task
- $0.17
- 168OpenAIDossier
Score
GPT-5 Pro, Score: 18.3% (scale 0.0 to 100.0)18.3%- Cost per task
- $7.14
- 169OpenAIDossier
medium
Score
GPT-6 Luna, Score: 18.1% (scale 0.0 to 100.0)18.1%- Cost per task
- Not tested
- 170OpenAIDossier
high · thinking
Score
GPT-5.1, Score: 17.6% (scale 0.0 to 100.0)17.6%- Cost per task
- $1.17
- 171xAIDossier
low
Score
Grok 4.7, Score: 16.7% (scale 0.0 to 100.0)16.7%- Cost per task
- Not tested
- 172xAIDossier
thinking
Score
Grok 4 (0709), Score: 16% (scale 0.0 to 100.0)16%- Cost per task
- Not tested
- 173AnthropicDossier
thinking · 8,000 budget
Score
Opus 4.5, Score: 13.9% (scale 0.0 to 100.0)13.9%- Cost per task
- $0.48
- 174Thinking MachinesDossier
medium
Score
Inkling Small, Score: 13.6% (scale 0.0 to 100.0)13.6%- Cost per task
- Not tested
- 175AnthropicDossier
32,000 budget
Score
Sonnet 4.5, Score: 13.6% (scale 0.0 to 100.0)13.6%- Cost per task
- $0.76
- 176AlibabaDossier
medium
Score
Qwen3.8-27B, Score: 13.2% (scale 0.0 to 100.0)13.2%- Cost per task
- Not tested
- 177OpenAIDossier
high
Score
GPT-5.4 mini, Score: 13.2% (scale 0.0 to 100.0)13.2%- Cost per task
- $0.56
- 178GoogleDossier
medium
Score
Gemini 3 Flash Preview, Score: 12.8% (scale 0.0 to 100.0)12.8%- Cost per task
- Not tested
- 179Moonshot AIDossier
low
Score
Kimi K3, Score: 12.4% (scale 0.0 to 100.0)12.4%- Cost per task
- $0.25
- 180MetaDossier
low
Score
Muse Spark Open, Score: 12.2% (scale 0.0 to 100.0)12.2%- Cost per task
- Not tested
- 181Moonshot AIDossier
Score
Kimi K2.5, Score: 11.8% (scale 0.0 to 100.0)11.8%- Cost per task
- $0.28
- 182GoogleDossier
high
Score
Gemini 3.5 Flash-Lite, Score: 10.3% (scale 0.0 to 100.0)10.3%- Cost per task
- Not tested
- 183OpenAIDossier
high
Score
GPT-5, Score: 9.9% (scale 0.0 to 100.0)9.9%- Cost per task
- $0.73
- 184OpenAIDossier
low
Score
GPT-5.2, Score: 9.7% (scale 0.0 to 100.0)9.7%- Cost per task
- $0.26
- 185AnthropicDossier
medium
Score
Haiku 5.5, Score: 9.4% (scale 0.0 to 100.0)9.4%- Cost per task
- Not tested
- 186GoogleDossier
minimal
Score
Gemini 3.5 Flash, Score: 8.9% (scale 0.0 to 100.0)8.9%- Cost per task
- $0.11
- 187AnthropicDossier
16,000 budget
Score
Opus 4, Score: 8.6% (scale 0.0 to 100.0)8.6%- Cost per task
- $1.93
- 188AnthropicDossier
none · thinking
Score
Opus 4.5, Score: 7.8% (scale 0.0 to 100.0)7.8%- Cost per task
- $0.22
- 189OpenAIDossier
medium
Score
GPT-5, Score: 7.5% (scale 0.0 to 100.0)7.5%- Cost per task
- $0.45
- 190OpenAIDossier
medium
Score
GPT-5.6 Luna, Score: 7.4% (scale 0.0 to 100.0)7.4%- Cost per task
- $0.11
- 191AnthropicDossier
16,000 budget
Score
Sonnet 4.5, Score: 6.9% (scale 0.0 to 100.0)6.9%- Cost per task
- $0.35
- 191AnthropicDossier
8,000 budget
Score
Sonnet 4.5, Score: 6.9% (scale 0.0 to 100.0)6.9%- Cost per task
- $0.23
- 193OpenAIDossier
medium · thinking
Score
GPT-5.1, Score: 6.5% (scale 0.0 to 100.0)6.5%- Cost per task
- $0.42
- 193OpenAIDossier
high
Score
o3, Score: 6.5% (scale 0.0 to 100.0)6.5%- Cost per task
- $0.83
- 195ReflectionDossier
medium
Score
Beam 1.0, Score: 6.4% (scale 0.0 to 100.0)6.4%- Cost per task
- Not tested
- 196SamsungDossier
Score
Tiny Recursion Model, Score: 6.3% (scale 0.0 to 100.0)6.3%- Cost per task
- $2.10
- 197OpenAIDossier
high
Score
o4-mini, Score: 6.1% (scale 0.0 to 100.0)6.1%- Cost per task
- $0.86
- 198AnthropicDossier
16,000 budget
Score
Claude Sonnet 4, Score: 5.9% (scale 0.0 to 100.0)5.9%- Cost per task
- $0.49
- 199AnthropicDossier
1,000 budget
Score
Sonnet 4.5, Score: 5.8% (scale 0.0 to 100.0)5.8%- Cost per task
- $0.14
- 200OpenAIDossier
xhigh
Score
GPT-5.4 nano, Score: 5.7% (scale 0.0 to 100.0)5.7%- Cost per task
- $0.16
- 200OpenAIDossier
xhigh
Score
GPT-5.4 nano, Score: 5.7% (scale 0.0 to 100.0)5.7%- Cost per task
- Not tested
- 202xAIDossier
Score
Grok 4 Fast, Score: 5.3% (scale 0.0 to 100.0)5.3%- Cost per task
- $0.061
- 203GoogleDossier
medium
Score
Gemini 3.5 Flash-Lite, Score: 5.3% (scale 0.0 to 100.0)5.3%- Cost per task
- Not tested
- 204OpenAIDossier
low
Score
GPT-5.6 Luna, Score: 5.1% (scale 0.0 to 100.0)5.1%- Cost per task
- $0.070
- 205Thinking MachinesDossier
low
Score
Inkling Small, Score: 4.9% (scale 0.0 to 100.0)4.9%- Cost per task
- Not tested
- 206GoogleDossier
32,000 budget
Score
Gemini 2.5 Pro, Score: 4.9% (scale 0.0 to 100.0)4.9%- Cost per task
- $0.76
- 206Z.aiDossier
Score
GLM-5, Score: 4.9% (scale 0.0 to 100.0)4.9%- Cost per task
- $0.27
- 206MiniMaxDossier
Score
MiniMax M2.5, Score: 4.9% (scale 0.0 to 100.0)4.9%- Cost per task
- $0.17
- 206OpenAIDossier
high
Score
o3-pro, Score: 4.9% (scale 0.0 to 100.0)4.9%- Cost per task
- $7.55
- 210OpenAIDossier
low
Score
GPT-6 Luna, Score: 4.6% (scale 0.0 to 100.0)4.6%- Cost per task
- Not tested
- 211AnthropicDossier
8,000 budget
Score
Opus 4, Score: 4.5% (scale 0.0 to 100.0)4.5%- Cost per task
- $1.16
- 212OpenAIDossier
high
Score
GPT-5 mini, Score: 4.4% (scale 0.0 to 100.0)4.4%- Cost per task
- $0.20
- 212OpenAIDossier
medium
Score
GPT-5.4 mini, Score: 4.4% (scale 0.0 to 100.0)4.4%- Cost per task
- $0.33
- 214DeepSeekDossier
Score
DeepSeek V3.2, Score: 4% (scale 0.0 to 100.0)4%- Cost per task
- $0.12
- 214GoogleDossier
16,000 budget
Score
Gemini 2.5 Pro, Score: 4% (scale 0.0 to 100.0)4%- Cost per task
- $0.71
- 214OpenAIDossier
medium
Score
GPT-5 mini, Score: 4% (scale 0.0 to 100.0)4%- Cost per task
- $0.063
- 214AnthropicDossier
32,000 budget
Score
Haiku 4.5, Score: 4% (scale 0.0 to 100.0)4%- Cost per task
- $0.38
- 218Thinking MachinesDossier
minimal
Score
Inkling Small, Score: 4% (scale 0.0 to 100.0)4%- Cost per task
- Not tested
- 219AnthropicDossier
Score
Sonnet 4.5, Score: 3.8% (scale 0.0 to 100.0)3.8%- Cost per task
- $0.13
- 220OpenAIDossier
high
Score
GPT-5.4 nano, Score: 3.6% (scale 0.0 to 100.0)3.6%- Cost per task
- $0.13
- 221GoogleDossier
minimal
Score
Gemini 3 Flash Preview, Score: 3.3% (scale 0.0 to 100.0)3.3%- Cost per task
- Not tested
- 222OpenAIDossier
high
Score
o3-mini, Score: 3% (scale 0.0 to 100.0)3%- Cost per task
- $0.55
- 223OpenAIDossier
medium
Score
o3, Score: 3% (scale 0.0 to 100.0)3%- Cost per task
- $0.48
- 224GoogleDossier
8,000 budget
Score
Gemini 2.5 Pro, Score: 2.9% (scale 0.0 to 100.0)2.9%- Cost per task
- $0.44
- 225AnthropicDossier
16,000 budget
Score
Haiku 4.5, Score: 2.8% (scale 0.0 to 100.0)2.8%- Cost per task
- $0.14
- 226ReflectionDossier
low
Score
Beam 1.0, Score: 2.8% (scale 0.0 to 100.0)2.8%- Cost per task
- Not tested
- 226AnthropicDossier
low
Score
Haiku 5.5, Score: 2.8% (scale 0.0 to 100.0)2.8%- Cost per task
- Not tested
- 228GoogleDossier
minimal
Score
Gemini 3.6 Flash, Score: 2.6% (scale 0.0 to 100.0)2.6%- Cost per task
- Not tested
- 229OpenAIDossier
high
Score
GPT-5 nano, Score: 2.6% (scale 0.0 to 100.0)2.6%- Cost per task
- $0.030
- 230GoogleDossier
23,000 budget
Score
Gemini 2.5 Flash Preview (05-20), Score: 2.5% (scale 0.0 to 100.0)2.5%- Cost per task
- $0.32
- 231OpenAIDossier
medium
Score
o4-mini, Score: 2.4% (scale 0.0 to 100.0)2.4%- Cost per task
- $0.23
- 232GoogleDossier
1,000 budget
Score
Gemini 2.5 Flash Preview (05-20), Score: 2.2% (scale 0.0 to 100.0)2.2%- Cost per task
- $0.030
- 233AnthropicDossier
8,000 budget
Score
Claude Sonnet 4, Score: 2.1% (scale 0.0 to 100.0)2.1%- Cost per task
- $0.27
- 233GoogleDossier
8,000 budget
Score
Gemini 2.5 Flash Preview (05-20), Score: 2.1% (scale 0.0 to 100.0)2.1%- Cost per task
- $0.20
- 235DeepSeekDossier
none
Score
DeepSeek V4-Flash 0731, Score: 2.1% (scale 0.0 to 100.0)2.1%- Cost per task
- Not tested
- 235DeepSeekDossier
none
Score
DeepSeek V4.1 Flash 1017, Score: 2.1% (scale 0.0 to 100.0)2.1%- Cost per task
- Not tested
- 237OpenAIDossier
medium
Score
o3-mini, Score: 2.1% (scale 0.0 to 100.0)2.1%- Cost per task
- $0.28
- 238OpenAIDossier
low
Score
o3-pro, Score: 2.1% (scale 0.0 to 100.0)2.1%- Cost per task
- $2.23
- 239OpenAIDossier
low
Score
o3, Score: 2% (scale 0.0 to 100.0)2%- Cost per task
- $0.23
- 240GoogleDossier
16,000 budget
Score
Gemini 2.5 Flash Preview (05-20), Score: 2% (scale 0.0 to 100.0)2%- Cost per task
- $0.32
- 241OpenAIDossier
low
Score
GPT-5, Score: 1.9% (scale 0.0 to 100.0)1.9%- Cost per task
- $0.19
- 241OpenAIDossier
low
Score
GPT-5, Score: 1.9% (scale 0.0 to 100.0)1.9%- Cost per task
- $0.19
- 241OpenAIDossier
low · thinking
Score
GPT-5.1, Score: 1.9% (scale 0.0 to 100.0)1.9%- Cost per task
- $0.13
- 241OpenAIDossier
medium
Score
GPT-5.4 nano, Score: 1.9% (scale 0.0 to 100.0)1.9%- Cost per task
- $0.060
- 241OpenAIDossier
medium
Score
o3-pro, Score: 1.9% (scale 0.0 to 100.0)1.9%- Cost per task
- $4.74
- 246GoogleDossier
Score
Gemini 2.5 Flash Preview (05-20), Score: 1.7% (scale 0.0 to 100.0)1.7%- Cost per task
- $0.057
- 247OpenAIDossier
minimal
Score
GPT-5 mini, Score: 1.7% (scale 0.0 to 100.0)1.7%- Cost per task
- $0.009
- 247AnthropicDossier
8,000 budget
Score
Haiku 4.5, Score: 1.7% (scale 0.0 to 100.0)1.7%- Cost per task
- $0.091
- 247OpenAIDossier
low
Score
o4-mini, Score: 1.7% (scale 0.0 to 100.0)1.7%- Cost per task
- $0.050
- 250OpenAIDossier
none
Score
GPT-6 Sol, Score: 1.7% (scale 0.0 to 100.0)1.7%- Cost per task
- Not tested
- 251OpenAIDossier
low
Score
GPT-5.4 nano, Score: 1.5% (scale 0.0 to 100.0)1.5%- Cost per task
- $0.010
- 252GoogleDossier
low
Score
Gemini 3.5 Flash-Lite, Score: 1.5% (scale 0.0 to 100.0)1.5%- Cost per task
- Not tested
- 252AlibabaDossier
none
Score
Qwen3.8-27B, Score: 1.5% (scale 0.0 to 100.0)1.5%- Cost per task
- Not tested
- 254DeepSeekDossier
Score
DeepSeek R1 (Jan '25), Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.080
- 254GoogleDossier
Score
Gemini 2.0 Flash (001), Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.004
- 256AnthropicDossier
Score
Claude Sonnet 4, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.13
- 256OpenAIDossier
Score
Codex mini, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.23
- 256AnthropicDossier
Score
Opus 4, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.64
- 259DeepSeekDossier
none
Score
DeepSeek V4.1 Flash, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- Not tested
- 259GoogleDossier
low
Score
Gemini 3 Flash Preview, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- Not tested
- 259AnthropicDossier
Score
Haiku 4.5, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.043
- 259AnthropicDossier
1,000 budget
Score
Haiku 4.5, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.047
- 259AlibabaDossier
Score
Qwen3 235B A22B 2507 Instruct, Score: 1.3% (scale 0.0 to 100.0)1.3%- Cost per task
- $0.004
- 264DeepSeekDossier
Score
DeepSeek R1 0528, Score: 1.1% (scale 0.0 to 100.0)1.1%- Cost per task
- $0.053
- 265OpenAIDossier
low
Score
GPT-5.4 mini, Score: 1.1% (scale 0.0 to 100.0)1.1%- Cost per task
- $0.060
- 266AnthropicDossier
8,000 budget
Score
Claude 3.7 Sonnet, Score: 0.9% (scale 0.0 to 100.0)0.9%- Cost per task
- $0.36
- 267OpenAIDossier
medium
Score
GPT-5 nano, Score: 0.9% (scale 0.0 to 100.0)0.9%- Cost per task
- $0.014
- 268AnthropicDossier
1,000 budget
Score
Claude Sonnet 4, Score: 0.9% (scale 0.0 to 100.0)0.9%- Cost per task
- $0.14
- 269DeepSeekDossier
none
Score
DeepSeek V4 Pro 0813, Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- Not tested
- 269GoogleDossier
minimal
Score
Gemini 3.5 Flash-Lite, Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- Not tested
- 271OpenAIDossier
low
Score
GPT-5 mini, Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- $0.019
- 271OpenAIDossier
Score
GPT-5.2, Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- Not tested
- 271OpenAIDossier
Score
o1-mini, Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- $0.19
- 274GoogleDossier
Score
Gemini 1.5 Pro (002), Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- $0.040
- 274OpenAIDossier
Score
GPT-4.5 Preview, Score: 0.8% (scale 0.0 to 100.0)0.8%- Cost per task
- $2.10
- 276AnthropicDossier
16,000 budget
Score
Claude 3.7 Sonnet, Score: 0.7% (scale 0.0 to 100.0)0.7%- Cost per task
- $0.51
- 277OpenAIDossier
Score
GPT-4.1, Score: 0.4% (scale 0.0 to 100.0)0.4%- Cost per task
- $0.069
- 277OpenAIDossier
none · thinking
Score
GPT-5.1, Score: 0.4% (scale 0.0 to 100.0)0.4%- Cost per task
- $0.058
- 277xAIDossier
low
Score
Grok 3 mini, Score: 0.4% (scale 0.0 to 100.0)0.4%- Cost per task
- $0.013
- 280AnthropicDossier
1,000 budget
Score
Claude 3.7 Sonnet, Score: 0.4% (scale 0.0 to 100.0)0.4%- Cost per task
- $0.14
- 281AnthropicDossier
Score
Claude 3.7 Sonnet, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.12
- 281GoogleDossier
1,000 budget
Score
Gemini 2.5 Pro Preview (06-05), Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.089
- 281OpenAIDossier
Score
GPT-4.1 mini, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.014
- 281OpenAIDossier
Score
GPT-4.1 nano, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.004
- 281OpenAIDossier
Score
GPT-4o (Nov '24), Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.080
- 281OpenAIDossier
Score
GPT-4o mini, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.010
- 281OpenAIDossier
minimal
Score
GPT-5, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.056
- 281OpenAIDossier
low
Score
GPT-5 nano, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.003
- 281OpenAIDossier
minimal
Score
GPT-5 nano, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.003
- 281OpenAIDossier
none
Score
GPT-6 Luna, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- Not tested
- 281xAIDossier
Score
Grok 3, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.14
- 281Thinking MachinesDossier
none
Score
Inkling Small, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- Not tested
- 281MetaDossier
Score
Llama 4 Maverick, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.012
- 281MetaDossier
Score
Llama 4 Scout, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.006
- 281MistralDossier
Score
Magistral Medium (2506), Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- Not tested
- 281MistralDossier
thinking
Score
Magistral Medium (2506), Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- Not tested
- 281MistralDossier
Score
Magistral Small (2506), Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.049
- 281OpenAIDossier
low
Score
o3-mini, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.062
- 281AnthropicDossier
1,000 budget
Score
Opus 4, Score: 0% (scale 0.0 to 100.0)0%- Cost per task
- $0.75