| Model | TTFT p50 | TTFT p95 | Latency | Tok/s | Errors | N |
|---|---|---|---|---|---|---|
|
anthropic/claude-opus-4.6
|
1647ms | 3798ms | 2026ms | 55.9 | 60 | 626 |
|
anthropic/claude-opus-4.7
|
2036ms | 5345ms | 2254ms | 86.8 | 106 | 845 |
|
anthropic/claude-opus-4.8
|
1245ms | 3310ms | 1401ms | 97.0 | 22 | 243 |
|
anthropic/claude-sonnet-4.6
|
2017ms | 4433ms | 2485ms | 44.6 | 106 | 845 |
|
deepseek/deepseek-v3.2
|
1423ms | 6230ms | 2128ms | 32.0 | 6 | 945 |
|
deepseek/deepseek-v4-flash
|
848ms | 5079ms | 2000ms | 63.7 | 84 | 867 |
|
deepseek/deepseek-v4-pro
|
0ms | 4409ms | 2353ms | 13.3 | 4 | 947 |
|
google/gemini-2.0-flash-001
|
414ms | 1148ms | 466ms | 215.6 | 36 | 146 |
|
google/gemini-2.5-flash
|
416ms | 5610ms | 485ms | 192.9 | 82 | 869 |
|
google/gemini-2.5-flash-lite
|
329ms | 1402ms | 392ms | 191.9 | 82 | 869 |
|
google/gemini-3.1-flash-lite
|
597ms | 2770ms | 621ms | 534.6 | 27 | 189 |
|
google/gemini-3.5-flash
|
0ms | 0ms | 1378ms | 12.3 | 31 | 522 |
|
openai/gpt-4o-mini
|
1358ms | 3118ms | 1482ms | 93.4 | 62 | 587 |
|
openai/gpt-5.4
|
1072ms | 2173ms | 1318ms | 51.1 | 44 | 258 |
|
openai/gpt-5.5
|
1543ms | 3148ms | 1875ms | 46.3 | 106 | 845 |
|
openai/gpt-oss-120b
|
0ms | 3398ms | 1550ms | 14.9 | 107 | 844 |
|
x-ai/grok-4-fast
|
2182ms | 5544ms | 2276ms | 2034.7 | 7 | 223 |
|
x-ai/grok-4.1-fast
|
2582ms | 4196ms | 2656ms | 2659.9 | 6 | 224 |
|
x-ai/grok-4.20
|
566ms | 2117ms | 655ms | 140.8 | 11 | 710 |
|
x-ai/grok-4.20-multi-agent
|
4024ms | 13939ms | 4384ms | 5289.2 | 1 | 143 |
|
x-ai/grok-4.3
|
1834ms | 5073ms | 1948ms | 1339.6 | 7 | 944 |
|
x-ai/grok-build-0.1
|
1988ms | 3646ms | 2136ms | 1710.9 | 1 | 576 |