- Context
- 205Ktokens
- Released
- 10mo ago
- Size
- 229Bparameters
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.
How it ranks
Against its predecessor, similarly priced models and the models ranked around it.
DeepSWE 1.1
Best pass@1 per model · Higher is better
Not evaluated in DeepSWE 1.1
Arena Text
Best Arena rating per model · Higher is better
Not ranked on Arena Text yet
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev yet
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Agent Arena
Best IPS score per model · Higher is better
Not ranked on Agent Arena yet
Terminal Bench
Best score per model · Higher is better
#30 of 49
- 66.5%
GPT-5.2-CodexSimilar release date - 64.3%
Gemini 3 Flash PreviewSimilar release date - 39.6%
DeepSeek V3.2Similar release date - 38.0%
Claude Opus 4.1Nearby rank - 36.6%
MiniMax-M2.1 - 35.7%
Kimi K2 ThinkingNearby rank - 35.5%Claude Haiku 4.5Nearby rank
- 33.4%
GLM 4.7Similar release date - 30.0%MiniMax-M2Predecessor
+6.6 pts vs MiniMax-M2 (predecessor) · Ahead of 1 of 4 models released around the same time
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
All published scores
- Terminal Bench#30 of 4936.6%
+6.6 pts vs MiniMax-M2 (predecessor)
- default36.6%Crux
- default29.2%Terminus 2
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.