Qwen 3.6 Plus vs Gemini 3.1 Pro Preview (02/26): Benchmark Comparison

Qwen 3.6 Plus has the higher score on 3 of 19 shared benchmarks; Gemini 3.1 Pro Preview (02/26) leads on 15.

The largest observed score gap is 22.17 pts on MedCode , where Gemini 3.1 Pro Preview (02/26) leads.

Reported ±1 standard-error ranges overlap on 6 of 19 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.

Open interactive comparison Read the methodology

Shared benchmark results

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

Benchmark Qwen 3.6 Plus Gemini 3.1 Pro Preview (02/26) Gap Reported uncertainty
Harvey's Legal Agent Benchmark 1.25% ±0.83 0.00% ±0.00 1.25 pts Reported ±1 SE ranges do not overlap
Legal Research Bench 14.90% ±2.48 20.67% ±2.81 5.77 pts Reported ±1 SE ranges do not overlap
LegalBench 84.23% ±0.42 87.40% ±0.33 3.16 pts Reported ±1 SE ranges do not overlap
EMB 32.87% ±2.81 52.62% ±2.97 19.75 pts Reported ±1 SE ranges do not overlap
Finance Agent (v2) 40.85% ±0.13 42.98% ±1.21 2.14 pts Reported ±1 SE ranges do not overlap
MortgageTax 67.97% ±0.91 69.40% ±0.91 1.43 pts Reported ±1 SE ranges overlap
Tax Agent Bench 32.84% ±2.75 37.84% ±3.10 5.00 pts Reported ±1 SE ranges overlap
TaxEval v2 74.73% ±0.85 72.88% ±0.86 1.85 pts Reported ±1 SE ranges do not overlap
MedCode 36.89% ±2.02 59.06% ±2.00 22.17 pts Reported ±1 SE ranges do not overlap
MedScribe 76.96% ±1.92 76.11% ±1.92 0.85 pts Reported ±1 SE ranges overlap
GPQA Diamond 87.37% ±1.67 95.45% ±1.05 8.08 pts Reported ±1 SE ranges do not overlap
MMLU Pro 87.67% ±0.32 90.99% ±0.28 3.32 pts Reported ±1 SE ranges do not overlap
MMMU Pro 84.16% ±0.88 88.21% ±0.78 4.05 pts Reported ±1 SE ranges do not overlap
SAGE 44.86% ±3.43 48.68% ±3.29 3.82 pts Reported ±1 SE ranges overlap
Code Migration 11.10% ±1.31 17.31% ±3.93 6.21 pts Reported ±1 SE ranges do not overlap
LiveCodeBench 85.95% ±0.98 88.48% ±0.93 2.53 pts Reported ±1 SE ranges do not overlap
ProgramBench 0.00% ±0.00 0.00% ±0.00 0.00 pts Reported ±1 SE ranges overlap
SWE-bench 73.40% ±1.98 78.80% ±1.83 5.40 pts Reported ±1 SE ranges do not overlap
Vibe Code Bench v1.1 25.57% ±3.91 32.03% ±4.34 6.47 pts Reported ±1 SE ranges overlap

Performance by category

Category Qwen 3.6 Plus average Gemini 3.1 Pro Preview (02/26) average
Legal 33.46% 36.02%
Finance 49.85% 55.14%
Healthcare 56.93% 67.59%
Academic 86.40% 91.55%
Education 44.86% 48.68%
Coding 39.20% 43.33%

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 Qwen 3.6 Plus cost Gemini 3.1 Pro Preview (02/26) cost Qwen 3.6 Plus latency Gemini 3.1 Pro Preview (02/26) latency
Harvey's Legal Agent Benchmark $3.94 $1.15 14m48s 7m17s
Legal Research Bench $0.70 $1.10 10m59s 4m02s
LegalBench N/A N/A 19.07s 10.06s
EMB $2.87 $3.77 31m14s 11m49s
Finance Agent (v2) $0.81 $1.59 10m12s 3m28s
MortgageTax N/A N/A 78.18s 23.62s
Tax Agent Bench $0.30 $0.30 6m18s 100.96s
TaxEval v2 N/A N/A 70.63s 41.93s
MedCode N/A N/A 56.22s 38.52s
MedScribe N/A N/A 2m54s 69.14s
GPQA Diamond N/A N/A 2m02s 65.76s
MMLU Pro N/A N/A 46.18s 23.91s
MMMU Pro N/A N/A 111.94s 76.99s
SAGE N/A N/A 3m49s 61.17s
Code Migration $4.78 $1.61 29m50s 12m01s
LiveCodeBench N/A N/A 7m56s 88.89s
ProgramBench N/A N/A 33m01s 12m36s
SWE-bench $0.87 $0.78 7m04s 5m12s
Vibe Code Bench v1.1 $5.45 $3.83 38m10s 20m12s

Results available only for Qwen 3.6 Plus

None.

Results available only for Gemini 3.1 Pro Preview (02/26)

  • Vals Index
  • ProofBench v1.1
  • BioMysteryBench
  • MysteryMechanism
  • Terminal-Bench Science
  • IOI
  • Terminal-Bench 4.0
  • Vibe Code Bench 1-100
  • Public Benefits Bench v1.1
Model details Qwen 3.6 Plus Model details Gemini 3.1 Pro Preview (02/26)