Skip to content
Weights Not Walls
Menu

FrontierMath-Erdos

Re-run by Epoch AI

No description yet: we only describe an eval set when we can do it correctly.

Kind
Run independently by Epoch AI, with public logs. Our own re-runs are not built yet.
Score shown
Epoch's column "Best score (across scorers)", as a percentage, higher is better. Error bars as the source gives them.
Results
16 in all: 1 for open-weight models, 15 for closed ones. 1 linked to a model page here.

Best open-weight result: moonshotai/Kimi-K3, 0.0%, number 16 of 16 results.

FrontierMath-Erdos results
#ModelWeightsSettingScoreDateSource
1gpt-6.2-astra_maxOpenAIclosedeffort max10.3%±3.728 Oct 2026Epoch AI
2gpt-6.1-sol_maxOpenAIclosedeffort max4.4%±2.51 Oct 2026Epoch AI
3gpt-6-astra_maxOpenAIclosedeffort max2.9%±2.128 Aug 2026Epoch AI
4claude-opus-5-5_maxAnthropicclosedeffort max2.9%±2.124 Sep 2026Epoch AI
5gemini-4-carbon_highGoogle DeepMindclosedeffort high2.9%±2.17 Nov 2026Epoch AI
6claude-sonnet-5-5_maxAnthropicclosedeffort max2.9%±2.18 Oct 2026Epoch AI
7gemini-4-argon_highGoogle DeepMindclosedeffort high1.5%±1.520 Oct 2026Epoch AI
8gpt-6-sol_maxOpenAIclosedeffort max1.5%±1.530 Sep 2026Epoch AI
9claude-fable-5_maxAnthropicclosedeffort max0.0%28 Aug 2026Epoch AI
10claude-fable-5-1_maxAnthropicclosedeffort max0.0%1 Sep 2026Epoch AI
11claude-opus-5_maxAnthropicclosedeffort max0.0%28 Aug 2026Epoch AI
12gemini-3.8-flash_highGoogle DeepMindclosedeffort high0.0%2 Sep 2026Epoch AI
13gpt-5.5_xhighOpenAIclosedeffort xhigh0.0%28 Aug 2026Epoch AI
14gpt-5.6-sol_maxOpenAIclosedeffort max0.0%28 Aug 2026Epoch AI
15grok-4.7_xhighxAIclosedeffort xhigh0.0%21 Sep 2026Epoch AI
16moonshotai/Kimi-K3Epoch: kimi-k3_max, Moonshotopeneffort max0.0%28 Aug 2026Epoch AI

Open-weight rows are shaded. Dates are when the result was run or evaluated, where the data says. Data from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Epoch AI. Method