SShogo Bench

GSO-Bench

Software optimisation: make a real codebase measurably faster without breaking it.

Agent Index weight
4%
in the Agentic coding pillar
Models tested
30
from the benchmark’s leaderboard and reports
Normalised for the index
0 → 0, 1 → 100
Official site

Results

#ModelScoreNormalisedHarnessCost/taskDate
1Claude Fable 5.1 Supported
Anthropic
88.2%OpenHands—Sep 27, 2026
2GPT-6 Astra Supported
OpenAI
79.4%OpenHands—Sep 27, 2026
3Claude Fable 5 Supported
Anthropic
78.4%OpenHands—Sep 27, 2026
4GPT-5.6 Sol Supported
OpenAI
76.5%OpenHands—Sep 27, 2026
5Claude Opus 4.8 Supported
Anthropic
47.1%OpenHands—Jul 12, 2026
6Claude Opus 4.7 Supported
Anthropic
44.1%OpenHands—Apr 27, 2026
7Claude Opus 4.6 Supported
Anthropic
41.2%OpenHands—Apr 27, 2026
8GPT-5.5 Supported
OpenAI
40.2%OpenHands—Apr 27, 2026
9Claude Sonnet 5 Supported
Anthropic
37.3%OpenHands—Jul 12, 2026
10GPT-5.4 Supported
OpenAI
31.4%OpenHands—Mar 10, 2026
11GPT-5.2 Supported
OpenAI
27.5%OpenHands—Dec 18, 2025
12Claude Opus 4.5 (latest) Supported
Anthropic
26.5%OpenHands——
13Gemini 3.1 Pro Preview Supported
Google
22.6%OpenHands—Mar 9, 2026
14Gemini 3 Pro Preview Supported
Google
18.6%OpenHands—Nov 28, 2025
15Claude Sonnet 4.5 (latest) Supported
Anthropic
14.7%OpenHands—Oct 10, 2025
16GPT-5.1 Supported
OpenAI
13.7%OpenHands—Dec 18, 2025
17Gemini 3 Flash Preview Supported
Google
9.8%OpenHands—Dec 19, 2025
18o3 Supported
OpenAI
8.8%OpenHands—Jun 9, 2025
19Claude-Opus-4 Supported
Anthropic
6.9%OpenHands——
20GPT-5 Supported
OpenAI
6.9%OpenHands—Aug 10, 2025
21Claude Sonnet 4 Supported
Anthropic
4.9%OpenHands——
22Kimi K2 0905 Estimated
Moonshot AI
4.9%OpenHands—Aug 26, 2025
23Qwen3 Coder 480B A35B Estimated
Alibaba (Qwen)
4.9%OpenHands—Sep 2, 2025
24Claude-Sonnet-3.5 Estimated
Anthropic
4.6%OpenHands—May 30, 2025
25Gemini 2.5 Pro Supported
Google
3.9%OpenHands—Oct 10, 2025
26Claude 3.7 Sonnet Supported
Anthropic
3.8%OpenHands——
27o4-mini Estimated
OpenAI
3.6%OpenHands—May 30, 2025
28GLM-4.5-Air
Z.ai (Zhipu)
2.9%OpenHands—Aug 26, 2025
29o3-mini Estimated
OpenAI
1.3%OpenHands—May 30, 2025
30GPT-4o (2024-08-06) Supported
OpenAI
0.0%OpenHands—May 30, 2025

For models without a GSO-Bench result, the index estimates one from Epoch’s Capabilities Index using a logistic fit on 28 models (residual SD 0.65 on the logit scale). Estimates are labelled and widen the model’s range.