Noometry

Coding benchmark

GSO leaderboard

As of October 2026, Claude Fable 5.1 has the highest published GSO score on Noometry at 88.2%, out of 31 models with results.

Last verified

About GSO

Software optimization tasks: the model must speed up real code bases while keeping them correct.

Category
Coding
Introduced
2025
Format
Performance patch
Unit
Percent (random guessing ≈ 0%)
Official site
gso-bench.github.io

Top 15 models

  1. Claude Fable 5.1 88.2%
  2. GPT-6 Astra 79.4%
  3. Claude Fable 5 78.4%
  4. GPT-5.6 Sol 76.5%
  5. Claude Opus 4.8 47.1%
  6. Claude Opus 4.7 44.1%
  7. Claude Opus 4.6 41.2%
  8. GPT-5.5 40.2%
  9. Claude Sonnet 5 37.3%
  10. GPT-5.4 31.4%
  11. GPT-5.2 27.4%
  12. Claude Opus 4.5 26.5%
  13. Gemini 3.1 Pro Preview 22.6%
  14. Gemini 3 Pro 18.6%
  15. Claude Sonnet 4.5 14.7%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Claude Fable 5.1 Anthropic88.2%Epoch AI
2GPT-6 Astra OpenAI79.4%Epoch AI
3Claude Fable 5 Anthropic78.4%Epoch AI
4GPT-5.6 Sol OpenAI76.5%Epoch AI
5Claude Opus 4.8 Anthropic47.1%Epoch AI
6Claude Opus 4.7 Anthropic44.1%Epoch AI
7Claude Opus 4.6 Anthropic41.2%highEpoch AI
8GPT-5.5 OpenAI40.2%xhighEpoch AI
9Claude Sonnet 5 Anthropic37.3%Epoch AI
10GPT-5.4 OpenAI31.4%xhighEpoch AI
11GPT-5.2 OpenAI27.4%highEpoch AI
12Claude Opus 4.5 Anthropic26.5%Epoch AI
13Gemini 3.1 Pro Preview Google22.6%Epoch AI
14Gemini 3 Pro Google18.6%Epoch AI
15Claude Sonnet 4.5 Anthropic14.7%Epoch AI
16GPT-5.1 OpenAI13.7%Epoch AI
17Gemini 3 Flash Preview Google9.8%Epoch AI
18o3 OpenAI8.8%highEpoch AI
19Claude Opus 4 Anthropic6.9%Epoch AI
20GPT-5 OpenAI6.9%highEpoch AI
21Claude Sonnet 4 Anthropic4.9%Epoch AI
22Kimi K2 (Jul 2025) Moonshot AI4.9%Epoch AI
23Qwen3-Coder 480B-A35B Instruct Alibaba (Qwen)4.9%Epoch AI
24Claude 3.5 Sonnet Anthropic4.6%Epoch AI
25Gemini 2.5 Pro Google3.9%Epoch AI
26Gemini 2.5 Pro Google3.9%Epoch AI
27Claude 3.7 Sonnet Anthropic3.8%Epoch AI
28o4-mini OpenAI3.6%highEpoch AI
29GLM-4.5-Air Z.ai (Zhipu)2.9%Epoch AI
30o3-mini OpenAI1.3%highEpoch AI
31GPT-4o OpenAI0%Epoch AI

Compare the leaders

Other coding benchmarks

Frequently asked questions

What does GSO measure?

Software optimization tasks: the model must speed up real code bases while keeping them correct.

Which model has the highest GSO score?

As of October 2026, Claude Fable 5.1 has the highest published GSO score on Noometry at 88.2%, out of 31 models with results.

What is the best open-weight model on GSO?

Kimi K2 (Jul 2025) has the highest GSO accuracy among open-weight models at 4.9%, ranking 22 of 31 overall.