Moonshot AIAuto-detectedKimi K2
Best configuration ranks #185 of 610 on the BenchLeader Index at 55.0 ±7.3 (thinking reasoning effort). Last measured 8 Sept 2026. Released 6 Nov 2025.
- Blended price
- $2.86/M
- $1.15 in · $8.00 out
- Output speed
- –
- First answer
- –
- Context
- 262k
- Overall index55
- Reasoning62
- Coding46
- Maths61
- Human preference62
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 84.2%#86 | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | 1453#90 | LMArena |
Coding
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| LMArena Coding | 1487#83 | LMArena | |
| LMArena WebDev | 1323#98 | LMArena |
Maths
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 83.1%#92 | Epoch AI Benchmarking Hub |
Human preference
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| LMArena Text | 1430#93 | LMArena |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0029 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.019 | – | – |
| Code edit | 6,000 / 1,500 | $0.019 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.101 | – | – |
| Structured extraction | 2,000 / 200 | $0.0039 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.