GDPval
GDPval results that Epoch AI republishes. Despite the column label (%), the values are 0 to 1 fractions.
FinanceGeneral text
Independent. Run by an operator independent of the model vendors.Epoch AI Benchmarking Hub by Epoch AIVersion 1Data as of 17 Nov 2026
No filters. Showing 11 of 11 rows.
1 OpenAIDossier | none | No harness | GPT-5.2, Win rate: 49.7% (scale 0.0 to 100.0)49.7% | 70.9% | Runs unstated | Cost kind unknown | Date not stated |
2 AnthropicDossier | No effort set | No harness | Opus 4.5, Win rate: 45.5% (scale 0.0 to 100.0)45.5% | 59.6% | Runs unstated | Cost kind unknown | Date not stated |
3 AnthropicDossier | No effort set | No harness | Opus 4.1, Win rate: 43.6% (scale 0.0 to 100.0)43.6% | 47.6% | Runs unstated | Cost kind unknown | Date not stated |
4 AnthropicDossier | No effort set | No harness | Sonnet 4.5, Win rate: 42.5% (scale 0.0 to 100.0)42.5% | 50.3% | Runs unstated | Cost kind unknown | Date not stated |
5 GoogleDossier | No effort set | No harness | Gemini 3 Pro Preview, Win rate: 40.3% (scale 0.0 to 100.0)40.3% | 53.5% | Runs unstated | Cost kind unknown | Date not stated |
6 OpenAIDossier | medium | No harness | GPT-5, Win rate: 34.8% (scale 0.0 to 100.0)34.8% | 38% | Runs unstated | Cost kind unknown | Date not stated |
7 OpenAIDossier | medium | No harness | o3, Win rate: 30.8% (scale 0.0 to 100.0)30.8% | 34.1% | Runs unstated | Cost kind unknown | Date not stated |
8 OpenAIDossier | high | No harness | o4-mini, Win rate: 25.3% (scale 0.0 to 100.0)25.3% | 27.8% | Runs unstated | Cost kind unknown | Date not stated |
9 GoogleDossier | No effort set | No harness | Gemini 2.5 Pro, Win rate: 23.3% (scale 0.0 to 100.0)23.3% | 25.5% | Runs unstated | Cost kind unknown | Date not stated |
10 xAIDossier | high | No harness | Grok 4 (0709), Win rate: 21.1% (scale 0.0 to 100.0)21.1% | 24.3% | Runs unstated | Cost kind unknown | Date not stated |
11 OpenAIDossier | No effort set | No harness | GPT-4o (Nov '24), Win rate: 9.9% (scale 0.0 to 100.0)9.9% | 12.3% | Runs unstated | Cost kind unknown | Date not stated |
- 1OpenAIDossier
none
Win rate
GPT-5.2, Win rate: 49.7% (scale 0.0 to 100.0)49.7%- Win or tie rate
- 70.9%
- 2AnthropicDossier
Win rate
Opus 4.5, Win rate: 45.5% (scale 0.0 to 100.0)45.5%- Win or tie rate
- 59.6%
- 3AnthropicDossier
Win rate
Opus 4.1, Win rate: 43.6% (scale 0.0 to 100.0)43.6%- Win or tie rate
- 47.6%
- 4AnthropicDossier
Win rate
Sonnet 4.5, Win rate: 42.5% (scale 0.0 to 100.0)42.5%- Win or tie rate
- 50.3%
- 5GoogleDossier
Win rate
Gemini 3 Pro Preview, Win rate: 40.3% (scale 0.0 to 100.0)40.3%- Win or tie rate
- 53.5%
- 6OpenAIDossier
medium
Win rate
GPT-5, Win rate: 34.8% (scale 0.0 to 100.0)34.8%- Win or tie rate
- 38%
- 7OpenAIDossier
medium
Win rate
o3, Win rate: 30.8% (scale 0.0 to 100.0)30.8%- Win or tie rate
- 34.1%
- 8OpenAIDossier
high
Win rate
o4-mini, Win rate: 25.3% (scale 0.0 to 100.0)25.3%- Win or tie rate
- 27.8%
- 9GoogleDossier
Win rate
Gemini 2.5 Pro, Win rate: 23.3% (scale 0.0 to 100.0)23.3%- Win or tie rate
- 25.5%
- 10xAIDossier
high
Win rate
Grok 4 (0709), Win rate: 21.1% (scale 0.0 to 100.0)21.1%- Win or tie rate
- 24.3%
- 11OpenAIDossier
Win rate
GPT-4o (Nov '24), Win rate: 9.9% (scale 0.0 to 100.0)9.9%- Win or tie rate
- 12.3%