gpt-oss-20bopen
OpenAI
30.0#353 of 427 overall
- Input / output
- US$ 0,02 / US$ 0,09 US$ per 1M tokens
- Context
- 131K tokens
- Release
- 08/05/2025 release date
- Speed
- 137 tok/s first token in 0.42 s
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| Arena text (Elo) weight 2 | 1287 | 12% | LMArena |
| Humanity's Last Exam weight 1 | 11.0 | 55% | Artificial Analysis |
| Terminal-Bench weight 1 | 0.0 | 22% | Artificial Analysis |
| GPQA Diamond | 68.8 | 48% | Artificial Analysis |
| Long-context reasoning | 34.7 | 35% | Artificial Analysis |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 36.0 | #131 | Terminal-Bench |
| Reasoning | 51.2 | #204 | Humanity's Last Exam, GPQA Diamond |
| Research | 42.7 | #230 | Long-context reasoning |
| Chat | 30.8 | #173 | Arena text (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.