DeepSeek V4.1 Flash
- Made by
- DeepSeek
- Released
- 10 September 2026
- Licence
- open
- Context
- 1M
- Input, per 1M tokens
- $0.3
- Output, per 1M tokens
- $1.2
How this score is made
- HealthBench Professional0.50750.7 out of 100runs −2.5 hardadjusted 53.2weight 0.446, supportingindependent leaderboardArtificial Analysis independent run, max reasoning; GPT-5.4 (low) judge, 4 repeats per task; length-adjusted (52.9 raw, 2,760 mean response chars)
- HealthBenchNo result here, and none is filled in.
- Health Optimization Bench: incretinNo result here, and none is filled in.
- SAFE-Teen3169.0 out of 100runs +4.8 easyadjusted 64.2weight 0.131, narrowofficial leaderboardNear its ceiling (leader 85.0), so it counts for less.no teen-aware prompt
- Adjusted average of 2 benchmarks, by weight
- 55.7
- Field average, counts for 42.9% with 2 of 4 benchmarks
- 55.3
- Index
- = 55.5
Benchmark by benchmark
HealthBench Professional33 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
- 0.507DeepSeek V4.1 Flash
37 modelsFull benchmark
SAFE-Teen (Vals AI)7 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
- 44Grok 4.7
17 models, lower is betterFull benchmark
Artificial Analysis Healthcare & Medical Index16 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
- 41DeepSeek V4.1 Flash (Reasoning, Max Effort)
29 modelsFull benchmark