Kimi K3
- Made by
- Moonshot AI
- Released
- 16 July 2026
- Licence
- Kimi K3 License (open weights)
- Size
- 2.8T total / 104B active
- Context
- 1M
- Input, per 1M tokens
- $3
- Output, per 1M tokens
- $15
How this score is made
- HealthBench Professional0.53253.2 out of 100runs −2.5 hardadjusted 55.7weight 0.446, supportingindependent leaderboardArtificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (56.9 raw, 3,250 mean response chars)
- HealthBenchNo result here, and none is filled in.
- Health Optimization Bench: incretin77.877.8 out of 100runs +4.0 easyadjusted 73.8weight 0.226, supportingofficial leaderboardNear its ceiling (leader 84.9), so it counts for less.
- SAFE-Teen4456.0 out of 100runs +4.8 easyadjusted 51.2weight 0.131, narrowofficial leaderboardNear its ceiling (leader 85.0), so it counts for less.no teen-aware prompt
- Adjusted average of 3 benchmarks, by weight
- 60.1
- Field average, counts for 33.3% with 3 of 4 benchmarks
- 55.3
- Index
- = 58.5
Benchmark by benchmark
HealthBench Professional28 of 37
- 0.703GPT-6 Astra (Anthropic run)
- 0.692Claude Sonnet 5.5
- 0.660Claude Fable 5
- 0.656Claude Opus 5.5
- 0.655GPT-6 Luna (Anthropic run)
- 0.648Claude Haiku 5.5
- 0.642GPT-6.1 Sol
- 0.627GPT-6.1 Terra
- 0.623Muse Wonder Full
- 0.532Kimi K3
37 modelsFull benchmark
Health Optimization Bench: incretin evidence synthesis7 of 17
- 84.9Claude Fable 5.1
- 83.8Claude Fable 5
- 82.2GPT-6 Astra (max)
- 81.3Grok 4.6
- 78.3Claude Opus 5
- 77.9GPT-5.6 Sol (max)
- 77.8Kimi K3
- 68.4Muse Spark
- 67.8Gemini 3.8 Flash
- 57.9Gemini 3.6
17 modelsFull benchmark
Health Optimization Bench6 of 15
- 70.9Claude Fable 5
- 69.3Claude Opus 5
- 66.8Grok 4.6
- 66.6GPT-5.6 Sol (max)
- 59.9Kimi K3
- 57.2Muse Spark
- 47.3Claude Fable 5.1
- 39.7Gemini 3.6
- 35.6Inkling
- 34.6Claude Sonnet 5
15 modelsFull benchmark
SAFE-Teen (Vals AI)11 of 17
- 15GPT-6.1 Sol
- 23Claude Sonnet 5.5
- 23GPT-5.6 Luna
- 26Muse Spark 1.3 (Extra High)
- 26Qwen 3.8 Max
- 27Claude Opus 5.5
- 31DeepSeek V4.1 Flash
- 33Mistral Large 4 Preview
- 40MiMo v2.6 Pro
- 44Kimi K3
17 models, lower is betterFull benchmark
Artificial Analysis Healthcare & Medical Index9 of 29
- 61Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
- 58Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
- 53Claude Opus 5 (Adaptive Reasoning, Max Effort)
- 52Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
- 52GPT-6 Astra (max)
- 50Muse Spark 1.3 (max)
- 47GLM-5.3 (max)
- 47Grok 4.7 (xhigh)
- 45GLM 5.3 Flash
- 45Kimi K3 (max)
29 modelsFull benchmark