- Context
- 262Ktokens
- Released
- 8mo ago
- Size
- 4Bparameters
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 Vision
Best Arena rating per model · Higher is better
Not ranked on Arena Vision 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
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#118 of 158
- 97.8%
GPT-5.4Similar release date - 95.6%
Gemini 3.1 Pro PreviewSimilar release date - 92.2%
Grok 4.20 (Reasoning)Similar release date - 84.4%
Qwen3.5-FlashSimilar release date - 57.8%
Claude Sonnet 3.7Nearby rank - 56.1%
Qwen3 8BPredecessor - 55.8%Qwen3.5 4B
- 55.6%
DeepSeek-R1-Distill-Qwen-32BNearby rank - 48.9%DeepSeek V3Nearby rank
-0.3 pts vs Qwen3 8B (predecessor) · Ahead of 0 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
- OTIS Mock AIME 2024-2025#118 of 15855.8%
-0.3 pts vs Qwen3 8B (predecessor)
- none55.8%
Source:Epoch AI evaluation
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.