gpt-oss-20b
OpenAIBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1288
- Among open models
- #89of 148
- Among all on Arena
- #264
- Votes
- 10,396
Measured on gpt-oss-20b, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Math1317#74#228677
- Chinese1315#80#242665
- Software & IT1311#87#2563.6K
- Medicine & health1310#83#239562
- Coding1306#87#2592.1K
- Applied math1306#81#241583
- English1303#93#2684.5K
- Science1297#88#2621.7K
- Hard prompts, English1292#90#2642.1K
- Business & finance1283#87#2541.8K
- Legal & government1280#96#274678
- Russian1278#84#256751
- Hard prompts1274#91#2674.7K
- Non-English1268#88#2625.9K
- Spanish1268#78#236283
- Multi-turn1268#95#2811.8K
- Expert1259#86#252504
- German1255#74#232217
- Polish1252#72#223807
- Long prompts1251#97#2932.1K
- Japanese1245#56#193246
- Writing & literature1238#99#2992.2K
- Instructions1236#99#2942.5K
- Korean1234#63#209227
- Excluding ties1222#88#2617.6K
- Media & sports1217#98#2971.7K
- Creative writing1202#105#3101.2K
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B

Molmo2-8BAi212878.7B
BenchClub runs
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/gpt-oss-20b-GGUF101 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/gpt-oss-20b-MXFP4-Q864 builds
- GPTQ · vLLM, SGLangpositron-ai/openai_gpt-oss-20b-ingest-best-gptq1 build
Most downloaded
- gpt-oss-20b-GGUFunsloth · Quantization615.1K downloads
- gpt-oss-20b-GGUFggml-org · Quantization401.3K downloads
- gpt-oss-20b-MXFP4-Q8mlx-community · Quantization176.8K downloads
- gpt-oss-20b-GGUFlmstudio-community · Quantization117.7K downloads
- gpt-oss-20b-unsloth-bnb-4bitunsloth · Quantization73.6K downloads
More from OpenAI
See more
gpt-oss-120b2.4M117B
Other 20–40B models
See more
Qwen3.8-27BQwen6.9M27.8B

gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B