LMArena Agent
Arena agent leaderboard: score with confidence interval, cost and output tokens per task, observation and session counts. One row per model and category.
No filters. Showing 64 of 64 rows.
1 AnthropicDossier | max | No harness | Fable 5.2, Agent score: 0.3 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.2 to 0.30.3(0.2–0.3) | $9.02 | 126,742.5 | 1690217 seeds | Cost kind unknown |
2[2–4] AnthropicDossier | max | No harness | Opus 5.5, Agent score: 0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.2 to 0.20.2(0.2–0.2) | $5.65 | 107,510.5 | 2583520 seeds | Cost kind unknown |
3[2–4] GoogleDossier | high | No harness | Gemini 4 Carbon, Agent score: 0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.2 to 0.20.2(0.2–0.2) | $1.35 | 44,991 | 10136564 seeds | Cost kind unknown |
4[2–8] AnthropicDossier | max | No harness | Sonnet 5.5, Agent score: 0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.2(0.1–0.2) | $3.46 | 150,642 | 1290203 seeds | Cost kind unknown |
5[3–7] GoogleDossier | high | No harness | Gemini 4 Hydrogen, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.1(0.1–0.2) | $1.53 | 64,700 | 1775553 seeds | Cost kind unknown |
6[4–9] AnthropicDossier | max | No harness | Fable 5.1, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.1(0.1–0.2) | $7.83 | 59,147.5 | 2429776 seeds | Cost kind unknown |
7[4–9] OpenAIDossier | max | No harness | GPT-6 Astra, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.1(0.1–0.2) | $5.28 | 32,278 | 1369610 seeds | Cost kind unknown |
8[5–9] AnthropicDossier | high | No harness | Opus 5.5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $2.12 | 31,743 | 6121926 seeds | Cost kind unknown |
9[8–10] OpenAIDossier | max | No harness | GPT-6.1 Sol, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $0.99 | 33,771.5 | 3156486 seeds | Cost kind unknown |
10[8–11] OpenAIDossier | max | No harness | GPT-6.1 Terra, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $0.87 | 45,319.5 | 9012698 seeds | Cost kind unknown |
11[10–11] GoogleDossier | high | No harness | Gemini 4 Argon, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $0.70 | 22,853.5 | 6558285 seeds | Cost kind unknown |
12[12–14] OpenAIDossier | medium | No harness | GPT-6.1 Sol, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $0.37 | 8,525 | 3092413 seeds | Cost kind unknown |
13[12–14] MetaDossier | max | No harness | Muse Wonder Full 1.0, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | Not tested | 29,708.3 | 5808390 seeds | Cost kind unknown |
14[12–18] AnthropicDossier | high | No harness | Sonnet 5.5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $0.88 | 22,997 | 1734631 seeds | Cost kind unknown |
15[14–19] OpenAIDossier | max | No harness | GPT-6 Sol, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10.1(0.0–0.1) | $1.85 | 39,154.5 | 3329023 seeds | Cost kind unknown |
16[14–18] AnthropicDossier | high | No harness | Fable 5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1) | $3.33 | 22,867.5 | 3536470 seeds | Cost kind unknown |
17[14–18] AnthropicDossier | max | No harness | Opus 5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10.1(0.0–0.1) | $4.50 | 61,124.3 | 4693643 seeds | Cost kind unknown |
18[15–19] TencentDossier | No effort set | No harness | Hy4, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10.1(0.0–0.1) | $0.57 | 59,209 | 3663825 seeds | Cost kind unknown |
19[18–21] OpenAIDossier | medium | No harness | GPT-6.1 Terra, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10(0.0–0.1) | $0.16 | 6,937.5 | 6110236 seeds | Cost kind unknown |
20[19–22] Moonshot AIDossier | max | No harness | Kimi K3.1 Pro, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10(0.0–0.1) | $1.16 | 32,837 | 6394684 seeds | Cost kind unknown |
21[19–22] OpenAIDossier | xhigh | No harness | GPT-5.6 Sol, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $1.59 | 22,826 | 6651633 seeds | Cost kind unknown |
22[21–26] Thinking MachinesDossier | No effort set | No harness | Inkling 2 Small, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.26 | 49,485 | 2068103 seeds | Cost kind unknown |
23[22–31] xAIDossier | xhigh | No harness | Grok 4.7, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $3.20 | 77,876 | 3760139 seeds | Cost kind unknown |
24[21–31] MetaDossier | max | No harness | Muse Ember, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.020 | 10,083 | 446781 seeds | Cost kind unknown |
25[23–31] XiaomiDossier | No effort set | No harness | MiMo-V2.6-Pro, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.16 | 47,607.5 | 5894831 seeds | Cost kind unknown |
26[23–31] GoogleDossier | high | No harness | Gemini 3.8 Flash, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.76 | 57,563 | 8581142 seeds | Cost kind unknown |
27[23–32] MetaDossier | max | No harness | Muse Spark 1.3, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.47 | 28,118 | 8884229 seeds | Cost kind unknown |
28[23–33] AnthropicDossier | high | No harness | Sonnet 5, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.00(-0.0–0.0) | $0.87 | 23,366 | 5245278 seeds | Cost kind unknown |
29[24–31] DeepSeekDossier | max | No harness | DeepSeek V4.1 Flash 1017, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.14 | 88,678.5 | 25876760 seeds | Cost kind unknown |
30[23–34] MetaDossier | max | No harness | Muse Wonder 1.0, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.00(-0.0–0.0) | $1.16 | 22,992 | 2258595 seeds | Cost kind unknown |
31[27–32] OpenAIDossier | max | No harness | GPT-6 Luna, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0) | $0.083 | 41,083 | 43309047 seeds | Cost kind unknown |
32[29–37] Z.aiDossier | max | No harness | GLM-5.3, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.00(-0.0–0.0) | $0.86 | 61,631.5 | 11337042 seeds | Cost kind unknown |
33[31–38] Moonshot AIDossier | max | No harness | Kimi K3, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0) | $0.89 | 25,449.5 | 16080247 seeds | Cost kind unknown |
34[31–38] TencentDossier | No effort set | No harness | Hy4 Preview, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0) | $0.43 | 49,617 | 12509642 seeds | Cost kind unknown |
35[31–39] AnthropicDossier | high | No harness | Haiku 5.5, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0) | $0.085 | 26,659 | 4531650 seeds | Cost kind unknown |
36[32–39] Z.aiDossier | max | No harness | GLM-5.2, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0) | $0.86 | 52,309 | 9366581 seeds | Cost kind unknown |
37[32–39] XiaomiDossier | No effort set | No harness | MiMo-V2.6-Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0) | $0.075 | 44,545 | 4085585 seeds | Cost kind unknown |
38[33–39] AlibabaDossier | No effort set | No harness | Qwen3.8-Max, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0) | $1.24 | 50,635 | 8683464 seeds | Cost kind unknown |
39[32–39] xAIDossier | xhigh | No harness | Grok 4.6, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0) | $1.33 | 33,480 | 3817161 seeds | Cost kind unknown |
40[40–44] OpenAIDossier | xhigh | No harness | GPT-5.6 Terra, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0) | $0.63 | 17,989 | 3851605 seeds | Cost kind unknown |
41[40–43] OpenAIDossier | medium | No harness | GPT-6 Luna, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0) | $0.025 | 9,507 | 12196381 seeds | Cost kind unknown |
42[40–44] GoogleDossier | high | No harness | Gemini 3.7 Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0) | $0.49 | 42,886 | 6162848 seeds | Cost kind unknown |
43[40–47] MiniMaxDossier | No effort set | No harness | MiniMax M3.1 Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0) | $0.21 | 69,867 | 2995449 seeds | Cost kind unknown |
44[42–45] Z.aiDossier | No effort set | No harness | GLM-5.3 Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0) | $0.14 | 46,332 | 13739000 seeds | Cost kind unknown |
45[43–48] StepFunDossier | No effort set | No harness | Step 5 Preview, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0(-0.1–-0.0) | $0.70 | 47,499 | 2938745 seeds | Cost kind unknown |
46[45–49] AlibabaDossier | No effort set | No harness | Qwen3.8 Flash Next, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0) | $0.23 | 63,527 | 17203977 seeds | Cost kind unknown |
47[45–50] AlibabaDossier | No effort set | No harness | Qwen3.8-27B, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0) | $0.39 | 53,374 | 8443389 seeds | Cost kind unknown |
48[45–51] GoogleDossier | No effort set | No harness | Gemini 3.1 Pro Preview, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0) | $0.59 | 13,424.5 | 2965057 seeds | Cost kind unknown |
49[45–53] MistralDossier | No effort set | No harness | Mistral Large 4, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0) | $0.32 | 26,158.8 | 562459 seeds | Cost kind unknown |
50[49–52] OpenAIDossier | low | No harness | GPT-6 Luna, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.010 | 3,746 | 3916474 seeds | Cost kind unknown |
51[45–56] ReflectionDossier | No effort set | No harness | Beam 1.0, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0) | Not tested | 15,788 | 696842 seeds | Cost kind unknown |
52[49–55] AlibabaDossier | No effort set | No harness | Qwen3.7 Max, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.28 | 15,367 | 2312095 seeds | Cost kind unknown |
53[50–56] TencentDossier | No effort set | No harness | Hy3, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.083 | 31,696 | 1237089 seeds | Cost kind unknown |
54[52–56] MetaDossier | No effort set | No harness | Muse Spark 1.1, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | Not tested | Not tested | 8427998 seeds | Cost kind unknown |
55[51–56] AlibabaDossier | No effort set | No harness | Qwen3.7 Plus, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.17 | 17,366 | 1304297 seeds | Cost kind unknown |
56[52–56] MetaDossier | xhigh | No harness | Muse Spark 1.2, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.41 | 25,558 | 3860984 seeds | Cost kind unknown |
57[56–58] MiniMaxDossier | No effort set | No harness | MiniMax M3, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.38 | 26,416 | 3778691 seeds | Cost kind unknown |
58[57–59] SynlanDossier | No effort set | No harness | Spark-X2.6, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1) | $0.083 | 33,500 | 1572280 seeds | Cost kind unknown |
59[58–60] MistralDossier | No effort set | No harness | Mistral Medium 3.5, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.1-0.1(-0.2–-0.1) | $0.30 | 12,776 | 668469 seeds | Cost kind unknown |
60[59–63] NVIDIADossier | No effort set | No harness | Nemotron 3 Ultra 550B A55B, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.1-0.2(-0.2–-0.1) | $0.13 | 8,222 | 243703 seeds | Cost kind unknown |
61[60–62] NVIDIADossier | No effort set | No harness | Nemotron 3.5 Super VL 120B A12B (NVFP4), Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.2-0.2(-0.2–-0.2) | Not tested | 14,558.5 | 2828817 seeds | Cost kind unknown |
62[61–63] Thinking MachinesDossier | No effort set | No harness | Inkling, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.2-0.2(-0.2–-0.2) | $0.30 | 14,214.5 | 1732484 seeds | Cost kind unknown |
63[61–63] Thinking MachinesDossier | No effort set | No harness | Inkling Small, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.2-0.2(-0.2–-0.2) | $0.16 | 20,902 | 567771 seeds | Cost kind unknown |
64 UpstageDossier | No effort set | No harness | Solar Pro 4, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.3 to -0.2-0.2(-0.3–-0.2) | $0.041 | 13,681 | 573412 seeds | Cost kind unknown |
- 1AnthropicDossier
max
Agent score
Fable 5.2, Agent score: 0.3 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.2 to 0.30.3(0.2–0.3)- Cost per task (median)
- $9.02
- Output tokens per task (median)
- 126,742.5
- 2AnthropicDossier
max
Agent score
Opus 5.5, Agent score: 0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.2 to 0.20.2(0.2–0.2)- Cost per task (median)
- $5.65
- Output tokens per task (median)
- 107,510.5
- 3GoogleDossier
high
Agent score
Gemini 4 Carbon, Agent score: 0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.2 to 0.20.2(0.2–0.2)- Cost per task (median)
- $1.35
- Output tokens per task (median)
- 44,991
- 4AnthropicDossier
max
Agent score
Sonnet 5.5, Agent score: 0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.2(0.1–0.2)- Cost per task (median)
- $3.46
- Output tokens per task (median)
- 150,642
- 5GoogleDossier
high
Agent score
Gemini 4 Hydrogen, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.1(0.1–0.2)- Cost per task (median)
- $1.53
- Output tokens per task (median)
- 64,700
- 6AnthropicDossier
max
Agent score
Fable 5.1, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.1(0.1–0.2)- Cost per task (median)
- $7.83
- Output tokens per task (median)
- 59,147.5
- 7OpenAIDossier
max
Agent score
GPT-6 Astra, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.20.1(0.1–0.2)- Cost per task (median)
- $5.28
- Output tokens per task (median)
- 32,278
- 8AnthropicDossier
high
Agent score
Opus 5.5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $2.12
- Output tokens per task (median)
- 31,743
- 9OpenAIDossier
max
Agent score
GPT-6.1 Sol, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $0.99
- Output tokens per task (median)
- 33,771.5
- 10OpenAIDossier
max
Agent score
GPT-6.1 Terra, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $0.87
- Output tokens per task (median)
- 45,319.5
- 11GoogleDossier
high
Agent score
Gemini 4 Argon, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $0.70
- Output tokens per task (median)
- 22,853.5
- 12OpenAIDossier
medium
Agent score
GPT-6.1 Sol, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $0.37
- Output tokens per task (median)
- 8,525
- 13MetaDossier
max
Agent score
Muse Wonder Full 1.0, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- Not tested
- Output tokens per task (median)
- 29,708.3
- 14AnthropicDossier
high
Agent score
Sonnet 5.5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $0.88
- Output tokens per task (median)
- 22,997
- 15OpenAIDossier
max
Agent score
GPT-6 Sol, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10.1(0.0–0.1)- Cost per task (median)
- $1.85
- Output tokens per task (median)
- 39,154.5
- 16AnthropicDossier
high
Agent score
Fable 5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.1 to 0.10.1(0.1–0.1)- Cost per task (median)
- $3.33
- Output tokens per task (median)
- 22,867.5
- 17AnthropicDossier
max
Agent score
Opus 5, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10.1(0.0–0.1)- Cost per task (median)
- $4.50
- Output tokens per task (median)
- 61,124.3
- 18TencentDossier
Agent score
Hy4, Agent score: 0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10.1(0.0–0.1)- Cost per task (median)
- $0.57
- Output tokens per task (median)
- 59,209
- 19OpenAIDossier
medium
Agent score
GPT-6.1 Terra, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10(0.0–0.1)- Cost per task (median)
- $0.16
- Output tokens per task (median)
- 6,937.5
- 20Moonshot AIDossier
max
Agent score
Kimi K3.1 Pro, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.10(0.0–0.1)- Cost per task (median)
- $1.16
- Output tokens per task (median)
- 32,837
- 21OpenAIDossier
xhigh
Agent score
GPT-5.6 Sol, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $1.59
- Output tokens per task (median)
- 22,826
- 22Thinking MachinesDossier
Agent score
Inkling 2 Small, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.26
- Output tokens per task (median)
- 49,485
- 23xAIDossier
xhigh
Agent score
Grok 4.7, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $3.20
- Output tokens per task (median)
- 77,876
- 24MetaDossier
max
Agent score
Muse Ember, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.020
- Output tokens per task (median)
- 10,083
- 25XiaomiDossier
Agent score
MiMo-V2.6-Pro, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.16
- Output tokens per task (median)
- 47,607.5
- 26GoogleDossier
high
Agent score
Gemini 3.8 Flash, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.76
- Output tokens per task (median)
- 57,563
- 27MetaDossier
max
Agent score
Muse Spark 1.3, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.47
- Output tokens per task (median)
- 28,118
- 28AnthropicDossier
high
Agent score
Sonnet 5, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.00(-0.0–0.0)- Cost per task (median)
- $0.87
- Output tokens per task (median)
- 23,366
- 29DeepSeekDossier
max
Agent score
DeepSeek V4.1 Flash 1017, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.14
- Output tokens per task (median)
- 88,678.5
- 30MetaDossier
max
Agent score
Muse Wonder 1.0, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.00(-0.0–0.0)- Cost per task (median)
- $1.16
- Output tokens per task (median)
- 22,992
- 31OpenAIDossier
max
Agent score
GPT-6 Luna, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval 0.0 to 0.00(0.0–0.0)- Cost per task (median)
- $0.083
- Output tokens per task (median)
- 41,083
- 32Z.aiDossier
max
Agent score
GLM-5.3, Agent score: 0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.00(-0.0–0.0)- Cost per task (median)
- $0.86
- Output tokens per task (median)
- 61,631.5
- 33Moonshot AIDossier
max
Agent score
Kimi K3, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0)- Cost per task (median)
- $0.89
- Output tokens per task (median)
- 25,449.5
- 34TencentDossier
Agent score
Hy4 Preview, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0)- Cost per task (median)
- $0.43
- Output tokens per task (median)
- 49,617
- 35AnthropicDossier
high
Agent score
Haiku 5.5, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0)- Cost per task (median)
- $0.085
- Output tokens per task (median)
- 26,659
- 36Z.aiDossier
max
Agent score
GLM-5.2, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0)- Cost per task (median)
- $0.86
- Output tokens per task (median)
- 52,309
- 37XiaomiDossier
Agent score
MiMo-V2.6-Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0)- Cost per task (median)
- $0.075
- Output tokens per task (median)
- 44,545
- 38AlibabaDossier
Agent score
Qwen3.8-Max, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0)- Cost per task (median)
- $1.24
- Output tokens per task (median)
- 50,635
- 39xAIDossier
xhigh
Agent score
Grok 4.6, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to 0.0-0(-0.0–0.0)- Cost per task (median)
- $1.33
- Output tokens per task (median)
- 33,480
- 40OpenAIDossier
xhigh
Agent score
GPT-5.6 Terra, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0)- Cost per task (median)
- $0.63
- Output tokens per task (median)
- 17,989
- 41OpenAIDossier
medium
Agent score
GPT-6 Luna, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0)- Cost per task (median)
- $0.025
- Output tokens per task (median)
- 9,507
- 42GoogleDossier
high
Agent score
Gemini 3.7 Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0)- Cost per task (median)
- $0.49
- Output tokens per task (median)
- 42,886
- 43MiniMaxDossier
Agent score
MiniMax M3.1 Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0)- Cost per task (median)
- $0.21
- Output tokens per task (median)
- 69,867
- 44Z.aiDossier
Agent score
GLM-5.3 Flash, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.0 to -0.0-0(-0.0–-0.0)- Cost per task (median)
- $0.14
- Output tokens per task (median)
- 46,332
- 45StepFunDossier
Agent score
Step 5 Preview, Agent score: -0 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0(-0.1–-0.0)- Cost per task (median)
- $0.70
- Output tokens per task (median)
- 47,499
- 46AlibabaDossier
Agent score
Qwen3.8 Flash Next, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0)- Cost per task (median)
- $0.23
- Output tokens per task (median)
- 63,527
- 47AlibabaDossier
Agent score
Qwen3.8-27B, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0)- Cost per task (median)
- $0.39
- Output tokens per task (median)
- 53,374
- 48GoogleDossier
Agent score
Gemini 3.1 Pro Preview, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0)- Cost per task (median)
- $0.59
- Output tokens per task (median)
- 13,424.5
- 49MistralDossier
Agent score
Mistral Large 4, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0)- Cost per task (median)
- $0.32
- Output tokens per task (median)
- 26,158.8
- 50OpenAIDossier
low
Agent score
GPT-6 Luna, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.010
- Output tokens per task (median)
- 3,746
- 51ReflectionDossier
Agent score
Beam 1.0, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.0-0.1(-0.1–-0.0)- Cost per task (median)
- Not tested
- Output tokens per task (median)
- 15,788
- 52AlibabaDossier
Agent score
Qwen3.7 Max, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.28
- Output tokens per task (median)
- 15,367
- 53TencentDossier
Agent score
Hy3, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.083
- Output tokens per task (median)
- 31,696
- 54MetaDossier
Agent score
Muse Spark 1.1, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- Not tested
- Output tokens per task (median)
- Not tested
- 55AlibabaDossier
Agent score
Qwen3.7 Plus, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.17
- Output tokens per task (median)
- 17,366
- 56MetaDossier
xhigh
Agent score
Muse Spark 1.2, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.41
- Output tokens per task (median)
- 25,558
- 57MiniMaxDossier
Agent score
MiniMax M3, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.38
- Output tokens per task (median)
- 26,416
- 58SynlanDossier
Agent score
Spark-X2.6, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.1 to -0.1-0.1(-0.1–-0.1)- Cost per task (median)
- $0.083
- Output tokens per task (median)
- 33,500
- 59MistralDossier
Agent score
Mistral Medium 3.5, Agent score: -0.1 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.1-0.1(-0.2–-0.1)- Cost per task (median)
- $0.30
- Output tokens per task (median)
- 12,776
- 60NVIDIADossier
Agent score
Nemotron 3 Ultra 550B A55B, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.1-0.2(-0.2–-0.1)- Cost per task (median)
- $0.13
- Output tokens per task (median)
- 8,222
- 61NVIDIADossier
Agent score
Nemotron 3.5 Super VL 120B A12B (NVFP4), Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.2-0.2(-0.2–-0.2)- Cost per task (median)
- Not tested
- Output tokens per task (median)
- 14,558.5
- 62Thinking MachinesDossier
Agent score
Inkling, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.2-0.2(-0.2–-0.2)- Cost per task (median)
- $0.30
- Output tokens per task (median)
- 14,214.5
- 63Thinking MachinesDossier
Agent score
Inkling Small, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.2 to -0.2-0.2(-0.2–-0.2)- Cost per task (median)
- $0.16
- Output tokens per task (median)
- 20,902
- 64UpstageDossier
Agent score
Solar Pro 4, Agent score: -0.2 (scale -1000000.0 to 1000000.0), 95% confidence interval -0.3 to -0.2-0.2(-0.3–-0.2)- Cost per task (median)
- $0.041
- Output tokens per task (median)
- 13,681
Unmatched upstream rows excluded from this board (3)
These upstream rows could not be mapped cleanly to the canonical model registry or reasoning effort enum.
| Raw name | Parsed model | Reason | Detail |
|---|---|---|---|
| Qwen4-Max (xHigh) | Qwen4-Max | no-alias | score |
| Qwen4-Max (xHigh) | Qwen4-Max | no-alias | cost-per-task |
| Qwen4-Max (xHigh) | Qwen4-Max | no-alias | output-tokens-per-task |