gpt-oss-120b
Open-weight 117B MoE, 5.1B active (OpenRouter). Negative LLM Chess Elo means weaker than the random-player anchor on that scale.
- Vendor
- OpenAI
- Kind
- llm
- Tier
- local
- Weights
- open
- Released
- 2025-08
- Context
- 131k tokens
Our Go rating
Not rated yet: ratings come from tournament games against bots of known strength. See the leaderboard.
Games here
No published game yet.
Benchmarks
| Measure | Value | Unit | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index (high) | 4 | index points | 2026-11 | Artificial Analysis Intelligence Index (current version, composite of |
Other games
| Measure | Value | Unit | As of | Source |
|---|---|---|---|---|
| LLM Chess (high), ±116 | -252 | Elo (chess.com-anchored) | 2026-11-05 | LLM Chess (Saplin) Elo vs random player and Komodo Dragon, chess.com-a |
How we run it
- works
ollama·gpt-oss:120b— local, 65 GB MXFP4; smoke test 2026-11-10 - untested
codex·gpt-oss:120b— `codex exec --oss --local-provider ollama` - disallowed
openrouter·openai/gpt-oss-120b— PA policy (2026-11-10): Anthropic/OpenAI/Google models run through their own agents or the free key, never OpenRouter unless PA asks explicitly