Kimi K3.1 Pro
Terminal-Bench 4.0's overall leader with released weights — at the cost of 28 tok/s
Benchmark scores
How it is measured →Ranked 10 · bars are scaled to the field maximum for that benchmark.
| Benchmarks | Score | Vs. best in field | Gap |
|---|---|---|---|
| AA Intelligence Index v5 Intelligence index | 46.0 | 77% | −14.0 pts |
| AA Intelligence Index v4.3.2 Intelligence index (legacy) | 55.1 | 96% | −2.5 pts |
| GPQA Diamond | — | — | not indexed |
| Terminal-Bench 4.0 Terminal-agent tasks | 67.2 | 100% | |
| LiveBench Design Document generation (DOCX/PPT/PDF) | 77.8 | 90% | −9.1 pts |
| Vals Index | — | — | not indexed |
Assessment
A post-trained version of Kimi K3 with the same parameter count (2.8T total / 104B active) and 1M context, priced a third below K3. It tops Terminal-Bench 4.0 at 67.2%; the full weights were released for download on 11-04 as promised, lifting the open-weights v5 ceiling from 32 to 46 and reshuffling the open leaderboard. A Highspeed variant (2-3x faster, $4/$20) also exists. Output speed of 28 tok/s remains the slowest among leading models, so long generations take noticeably longer.
At the same price
The four models closest on blended price, side by side.
| Model | v5 | Blended | tok/s | Score gap |
|---|---|---|---|---|
| Claude Sonnet 5.5Anthropic | 54.5 | $4.00 | 135 | +8.5 |
| GPT-6.1 SolOpenAI | 54.6 | $4.00 | 77 | +8.6 |
| Gemini 4 ArgonGoogle | 50.4 | $4.00 | 80 | +4.4 |
| Grok 4.7xAI | 34.3 | $3.00 | 105 | -11.7 |
Compare side by side
Line it up against other models on price, speed and every benchmark.
The comparison tool lines up to 4 models side by side with switchable normalisation — built for purchasing decisions.
Open the comparison tool → Back to leaderboard