EvoCode-Bench - Task Completion: leaderboard
EvoCode-Bench (2026) full-task completion: the percent of 26 multi-round coding tasks (5 to 15 rounds of evolving and conflicting requirements in one persistent workspace) that an agent carries through the final round without a failed cumulative check, in any of four attempts, each model in the Terminus-2 harness; higher is better.
Metric: Full-task completion (Comp, %): share of the 26 tasks in which at least one of four attempts passes the cumulative verifier at every round through the final one (fail-stop), 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 4.7 | High | 42.3 | #85 |
| 2 | GPT-5.5 | High | 38.5 | #54 |
| 3 | Claude Opus 4.6 | 34.6 | #113 | |
| 4 | Kimi K2.6 | 23.1 | #192 | |
| 5 | DeepSeek V4 Pro | High | 19.2 | #196 |
| 6 | GLM-5.1 | 15.4 | #198 | |
| 7 | Qwen 3.6 Plus | Thinking | 15.4 | #238 |
| 8 | Gemini 3.1 Pro (Preview) | High | 11.5 | #99 |
| 9 | MiMo-V2.5-Pro | High | 11.5 | #284 |
| 10 | Qwen 3.5 397B A17B | 0 | #264 | |
| 11 | MiniMax-M2.7 | 0 | #539 | |
| 12 | DeepSeek V4 Flash | High | 0 | #267 |
| 13 | Seed 2.0 Pro | High | 0 | #222 |
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-task-completion · How It Works · Data refreshed daily, snapshot 2026-11-21.