- input
- $0.02
- output
- $0.04
- Context
- 131Ktokens
- Released
- 2y ago
- Size
- 8Bparameters
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
Arena #348
- 1474
GLM 5.3 FlashSimilar price - 1230
Mixtral 8x22B InstructNearby rank - 1223
Aya Expanse 8BNearby rank - 1211
Llama 3.1 8B Instruct - 1200
Gemma 2 2B ITNearby rank - 1197Mixtral 8x7B Instruct v0.1Nearby rank
Ahead of 0 of 1 similarly priced model
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
GPQA diamond
Best score per model · Higher is better
#157 of 161
- 90.2%GLM 5.3 FlashSimilar price
- 35.5%
Qwen2.5 7B InstructNearby rank - 30.6%Mixtral 8x7B Instruct v0.1Nearby rank
- 27.0%Llama 3.1 8B Instruct
- 23.9%Llama 3.2 1B InstructNearby rank
- 23.2%Gemma 3 4BNearby rank
Ahead of 0 of 1 similarly priced model
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#155 of 158
- 93.9%GLM 5.3 FlashSimilar price
- 2.5%Qwen2.5 7B InstructNearby rank
- 1.8%
Claude Haiku 3Nearby rank - 1.7%Llama 3.1 8B Instruct
- 1.4%Gemma 2 27BNearby rank
- 0.6%Llama 3.2 1B InstructNearby rank
Ahead of 0 of 1 similarly priced model
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
- Arena TextArena #3481211
- default121195% CI 1207 to 1215 · 49,605 votes
- GPQA diamond#157 of 16127.0%
- default27.0%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#155 of 1581.7%
- default1.7%
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.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.