EvoCode-Bench - Single-Round: leaderboard
EvoCode-Bench (2026) single-round protocol: before each of 227 rounds of 26 evolving coding tasks, the workspace is fast-forwarded to the reference solution, and the agent (each model in the Terminus-2 harness) must pass the cumulative tests of that round in one attempt. Pass rate in percent; higher is better.
Metric: Single-round pass rate (SR, %): share of the 227 rounds solved in one attempt after Harbor fast-forwards the workspace to the reference solution of all earlier rounds, over the 26 stateful multi-round coding tasks of EvoCode-Bench (227 rounds, 5 to 15 per task, requirements that extend, correct or contradict earlier ones, cumulative executable verifiers), each model driving the Terminus-2 agent harness in a Harbor Docker workspace; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 78.9 | #113 | |
| 2 | Claude Opus 4.7 | High | 76.7 | #85 |
| 3 | GPT-5.5 | High | 74.4 | #54 |
| 4 | GLM-5.1 | 63.9 | #198 | |
| 5 | Kimi K2.6 | 59 | #192 | |
| 6 | Qwen 3.6 Plus | Thinking | 57.3 | #238 |
| 7 | DeepSeek V4 Pro | High | 56.4 | #196 |
| 8 | Gemini 3.1 Pro (Preview) | High | 46.7 | #99 |
| 9 | DeepSeek V4 Flash | High | 46.3 | #267 |
| 10 | Qwen 3.5 397B A17B | 44.1 | #264 | |
| 11 | MiniMax-M2.7 | 30 | #539 | |
| 12 | Seed 2.0 Pro | High | 23.8 | #222 |
| 13 | MiMo-V2.5-Pro | High | 7.9 | #284 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=evocode-bench-single-round · How It Works · Data refreshed daily, snapshot 2026-11-21.