DeepSeek V4.1 Flash 1017 vs MiMo V2.6 Pro: Benchmark Comparison

DeepSeek V4.1 Flash 1017 has the higher score on 9 of 13 shared benchmarks; MiMo V2.6 Pro leads on 4.

The largest observed score gap is 18.74 pts on Code Migration v1.1 , where DeepSeek V4.1 Flash 1017 leads.

Reported ±1 standard-error ranges overlap on 8 of 13 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.

Shared benchmark results

Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.

Benchmark DeepSeek V4.1 Flash 1017 MiMo V2.6 Pro Gap Reported uncertainty
Vals Index 61.26% ±1.05 57.81% ±1.24 3.44 pts Reported ±1 SE ranges do not overlap
Vals Finance Index 60.89% ±1.47 57.85% ±1.57 3.04 pts Reported ±1 SE ranges do not overlap
Vals Legal Index 71.86% ±1.82 72.14% ±1.83 0.28 pts Reported ±1 SE ranges overlap
HLAB-Vals-1.1 14.17% ±2.79 13.75% ±2.84 0.42 pts Reported ±1 SE ranges overlap
Legal Research Bench 45.19% ±3.46 47.12% ±3.47 1.92 pts Reported ±1 SE ranges overlap
EMB v1.1 69.17% ±2.40 67.35% ±2.90 1.83 pts Reported ±1 SE ranges overlap
Finance Agent v2.1 62.93% ±2.03 64.26% ±2.02 1.33 pts Reported ±1 SE ranges overlap
Tax Agent Bench 44.35% ±3.57 32.39% ±3.36 11.96 pts Reported ±1 SE ranges do not overlap
Code Migration v1.1 67.52% ±2.76 48.79% ±3.88 18.74 pts Reported ±1 SE ranges do not overlap
Terminal-Bench 4.0 31.82% ±2.62 31.31% ±3.07 0.51 pts Reported ±1 SE ranges overlap
Vibe Code Bench 1-100 v1.1 26.15% ±4.13 26.41% ±4.21 0.26 pts Reported ±1 SE ranges overlap
Vibe Code Bench v1.1 87.73% ±2.75 85.22% ±3.39 2.51 pts Reported ±1 SE ranges overlap
Access to Justice Benchmark 73.11% ±0.71 69.96% ±0.74 3.14 pts Reported ±1 SE ranges do not overlap

Performance by category

Category DeepSeek V4.1 Flash 1017 average MiMo V2.6 Pro average
Legal 29.68% 30.43%
Finance 58.82% 54.66%
Coding 53.31% 47.93%
Social Mobility 73.11% 69.96%

Cost and latency

Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.

Benchmark DeepSeek V4.1 Flash 1017 cost MiMo V2.6 Pro cost DeepSeek V4.1 Flash 1017 latency MiMo V2.6 Pro latency
Vals Index $0.66 $0.43 39m55s 1h13m
Vals Finance Index $0.42 $0.22 23m02s 30m48s
Vals Legal Index $0.59 $0.18 26m06s 29m02s
HLAB-Vals-1.1 $0.61 $0.22 22m08s 31m02s
Legal Research Bench $0.70 $0.18 35m07s 30m16s
EMB v1.1 $0.33 $0.33 32m52s 55m14s
Finance Agent v2.1 $0.47 $0.18 15m09s 11m22s
Tax Agent Bench $0.46 $0.13 21m04s 25m48s
Code Migration v1.1 $1.76 $0.99 2h21m 3h28m
Terminal-Bench 4.0 $0.54 $0.46 41m10s 2h42m
Vibe Code Bench 1-100 v1.1 $2.68 $1.32 1h40m 3h04m
Vibe Code Bench v1.1 $0.58 $1.04 16m14s 1h01m
Access to Justice Benchmark $0.09 $0.05 4m29s 12m08s

Results available only for DeepSeek V4.1 Flash 1017

  • CyberOffense

Results available only for MiMo V2.6 Pro

  • Immigration
  • MedCode
  • MedScribe
  • ProofBench v1.1
  • MysteryMechanism
  • Terminal-Bench-Science
  • SAGE
  • IOI
  • ProgramBench
  • SWE-bench Multimodal
  • CyberBench v1.1
  • SRE Bench
  • Financial Coaching Bench
  • Public Benefits Bench v1.1
Model details DeepSeek V4.1 Flash 1017 Model details MiMo V2.6 Pro