Anthropic: Claude Haiku 4.5 vs OpenAI: gpt-oss-120b
OpenAI: gpt-oss-120b wins on more metrics (5 of 7), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Haiku 4.5 | OpenAI: gpt-oss-120b |
|---|---|---|
| Intelligence Index | 23.7 | 23.8✓ |
| Coding Index | — | 30.4✓ |
| GPQA Diamond | 65% | 78%✓ |
| Design Arena Elo | 1153✓ | 1029 |
| Speed (tokens/sec) | — | — |
| Latency | — | — |
| Input price /M | $1.00 | $0.037✓ |
| Output price /M | $5.00 | $0.170✓ |
| Context window | 200K✓ | 131K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSON |
Frequently asked
Is Anthropic: Claude Haiku 4.5 better than OpenAI: gpt-oss-120b?
OpenAI: gpt-oss-120b wins on more metrics (5 of 7), but the right pick depends on what you optimize for — see the breakdown below.
What are the biggest differences between Anthropic: Claude Haiku 4.5 and OpenAI: gpt-oss-120b?
The table on this page compares Anthropic: Claude Haiku 4.5 and OpenAI: gpt-oss-120b metric by metric — intelligence benchmarks, coding score, speed, latency, context window and per-token price — with the winner marked on each row. Data refreshes hourly.