- input
- $0.078
- cached
- $0.07
- output
- $0.114
- Context
- 262Ktokens
- Released
- 8mo ago
- Size
- 9Bparameters
Cost/1M tokens
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
GPQA diamond
Best score per model · Higher is better
#90 of 161
- 91.0%
DeepSeek V4 Flash 0731Similar price - 79.7%
Claude Sonnet 3.7Nearby rank - 79.2%Claude Sonnet 4Nearby rank
- 79.0%
Qwen3.5-9B - 78.5%
GPT-5.4 NanoNearby rank - 77.6%
Seed 1.6Nearby rank - 56.8%
Qwen3 8BPredecessor - 56.1%
Phi 4Similar price - 39.5%
Gemma 3 12BSimilar price - 23.9%
Llama 3.2 1B InstructSimilar price
+22.2 pts vs Qwen3 8B (predecessor) · Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#112 of 158
- 94.4%DeepSeek V4 Flash 0731Similar price
- 62.8%Qwen3 30B A3BNearby rank
- 62.2%Qwen3 30B A3B Instruct 2507Nearby rank
- 61.7%Qwen3.5-9B
- 59.2%QwQ 32BNearby rank
- 58.3%
GLM 4.7 FlashNearby rank - 56.1%Qwen3 8BPredecessor
- 16.7%Gemma 3 12BSimilar price
- 13.8%Phi 4Similar price
- 0.6%Llama 3.2 1B InstructSimilar price
+5.6 pts vs Qwen3 8B (predecessor) · Ahead of 3 of 4 similarly priced models
Terminal Bench
Best score per model · Higher is better
#48 of 49
- 21.8%GPT-5 NanoSimilar price
- 18.7%gpt-oss-120bNearby rank
- 17.1%Gemini 2.5 FlashNearby rank
- 9.2%Qwen3.5-9B
- 3.4%gpt-oss-20bSimilar price
Ahead of 1 of 2 similarly priced models
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
- GPQA diamond#90 of 16179.0%
+22.2 pts vs Qwen3 8B (predecessor)
- none78.9%
- default79.0%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#112 of 15861.7%
+5.6 pts vs Qwen3 8B (predecessor)
- none61.7%
- default42.8%
Source:Epoch AI evaluation - Terminal Bench#48 of 499.2%
- default9.2%little-coder
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.