Leaderboard
Live benchmark results across AI providers — latency, throughput, and pass rates.
14 results
| Provider | Model | Test | Status | Latency (ms) | Tok/sec | In tokens | Out tokens | $/1M in | $/1M out |
|---|---|---|---|---|---|---|---|---|---|
| gemini | gemini-2.0-flash | code | fail | 294 | — | — | — | — | — |
| gemini | gemini-2.0-flash | reasoning | fail | 317 | — | — | — | — | — |
| gemini | gemini-2.0-flash | context | fail | 318 | — | — | — | — | — |
| gemini | gemini-2.0-flash | speed | fail | 375 | — | — | — | — | — |
| gemini | gemini-2.0-flash | ping | fail | 382 | — | — | — | — | — |
| gemini | gemini-2.0-flash | json | fail | 386 | — | — | — | — | — |
| gemini | gemini-2.0-flash | tool_use | fail | 390 | — | — | — | — | — |
| anthropic | claude-haiku-4-5-20251001 | ping | pass | 737 | 5.4 | 14 | 4 | 1.00 | 5.00 |
| anthropic | claude-haiku-4-5-20251001 | context | pass | 982 | 39.7 | 222 | 39 | 1.00 | 5.00 |
| anthropic | claude-haiku-4-5-20251001 | tool_use | pass | 1116 | 50.2 | 594 | 56 | 1.00 | 5.00 |
| anthropic | claude-haiku-4-5-20251001 | reasoning | pass | 1131 | 42.4 | 32 | 48 | 1.00 | 5.00 |
| anthropic | claude-haiku-4-5-20251001 | json | pass | 1131 | 41.6 | 59 | 47 | 1.00 | 5.00 |
| anthropic | claude-haiku-4-5-20251001 | code | pass | 2061 | 118.9 | 40 | 245 | 1.00 | 5.00 |
| anthropic | claude-haiku-4-5-20251001 | speed | pass | 5787 | 86.4 | 38 | 500 | 1.00 | 5.00 |