Skip to content
Weights Not Walls
Menu

SpireClimb

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; random guessing scores about 0.0%. Error bars as the source gives them.
Results
11 in all: 0 for open-weight models, 11 for closed ones. 0 linked to a model page here.

No open-weight model has a result on this set.

SpireClimb results
#ModelWeightsSettingScoreDateSource
1gpt-6.2-astra_maxOpenAIclosedeffort max41.3%±4.26 Nov 2026Epoch AI
2gpt-6-astra_maxOpenAIclosedeffort max34.0%±4.14 Nov 2026Epoch AI
3gpt-6.1-sol_maxOpenAIclosedeffort max23.8%±3.74 Nov 2026Epoch AI
4gpt-6.1-terra_maxOpenAIclosedeffort max22.3%±3.44 Nov 2026Epoch AI
5claude-fable-5-2_maxAnthropicclosedeffort max15.3%±3.16 Nov 2026Epoch AI
6gpt-6-sol_maxOpenAIclosedeffort max9.2%±2.45 Nov 2026Epoch AI
7gemini-4-hydrogen_xhighGoogle DeepMindclosedeffort xhigh7.7%±2.313 Nov 2026Epoch AI
8claude-opus-5-5_maxAnthropicclosedeffort max5.8%±2.04 Nov 2026Epoch AI
9claude-fable-5-1_maxAnthropicclosedeffort max2.0%±1.15 Nov 2026Epoch AI
10claude-sonnet-5-5_maxAnthropicclosedeffort max1.3%±0.95 Nov 2026Epoch AI
11gpt-6-luna_maxOpenAIclosedeffort max0.0%5 Nov 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