Qwen 3.6 Plus vs Gemini 3.5 Flash Lite: Benchmark Comparison
Qwen 3.6 Plus has the higher score on 10 of 19 shared benchmarks; Gemini 3.5 Flash Lite leads on 8.
The largest observed score gap is 11.60 pts on Vibe Code Bench v1.1 , where Gemini 3.5 Flash Lite leads.
Reported ±1 standard-error ranges overlap on 8 of 19 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 | Qwen 3.6 Plus | Gemini 3.5 Flash Lite | 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 | 13.94% ±2.41 | 0.96 pts | Reported ±1 SE ranges overlap |
| LegalBench | 84.23% ±0.42 | 84.07% ±0.44 | 0.16 pts | Reported ±1 SE ranges overlap |
| EMB | 32.87% ±2.81 | 43.23% ±3.10 | 10.36 pts | Reported ±1 SE ranges do not overlap |
| Finance Agent (v2) | 40.85% ±0.13 | 47.44% ±0.51 | 6.60 pts | Reported ±1 SE ranges do not overlap |
| MortgageTax | 67.97% ±0.91 | 68.68% ±0.91 | 0.72 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 32.84% ±2.75 | 37.45% ±3.12 | 4.61 pts | Reported ±1 SE ranges overlap |
| TaxEval v2 | 74.73% ±0.85 | 72.61% ±0.88 | 2.13 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 36.89% ±2.02 | 43.49% ±1.95 | 6.59 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 76.96% ±1.92 | 70.89% ±2.03 | 6.08 pts | Reported ±1 SE ranges do not overlap |
| GPQA Diamond | 87.37% ±1.67 | 83.84% ±1.85 | 3.54 pts | Reported ±1 SE ranges do not overlap |
| MMLU Pro | 87.67% ±0.32 | 85.84% ±0.34 | 1.83 pts | Reported ±1 SE ranges do not overlap |
| MMMU Pro | 84.16% ±0.88 | 83.58% ±0.89 | 0.58 pts | Reported ±1 SE ranges overlap |
| SAGE | 44.86% ±3.43 | 47.30% ±3.38 | 2.44 pts | Reported ±1 SE ranges overlap |
| Code Migration | 11.10% ±1.31 | 6.15% ±1.71 | 4.95 pts | Reported ±1 SE ranges do not overlap |
| LiveCodeBench | 85.95% ±0.98 | 79.01% ±1.10 | 6.94 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 | 75.00% ±1.94 | 1.60 pts | Reported ±1 SE ranges overlap |
| Vibe Code Bench v1.1 | 25.57% ±3.91 | 37.16% ±4.63 | 11.60 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Qwen 3.6 Plus average | Gemini 3.5 Flash Lite average |
|---|---|---|
| Legal | 33.46% | 32.67% |
| Finance | 49.85% | 53.88% |
| Healthcare | 56.93% | 57.19% |
| Academic | 86.40% | 84.42% |
| Education | 44.86% | 47.30% |
| Coding | 39.20% | 39.46% |
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 3.5 Flash Lite cost | Qwen 3.6 Plus latency | Gemini 3.5 Flash Lite latency |
|---|---|---|---|---|
| Harvey's Legal Agent Benchmark | $3.94 | $0.33 | 14m48s | 3m53s |
| Legal Research Bench | $0.70 | $0.12 | 10m59s | 59.20s |
| LegalBench | N/A | N/A | 19.07s | 1.67s |
| EMB | $2.87 | $1.23 | 31m14s | 8m14s |
| Finance Agent (v2) | $0.81 | $0.39 | 10m12s | 2m23s |
| MortgageTax | N/A | N/A | 78.18s | 4.88s |
| Tax Agent Bench | $0.30 | $0.08 | 6m18s | 47.46s |
| TaxEval v2 | N/A | N/A | 70.63s | 8.81s |
| MedCode | N/A | N/A | 56.22s | 6.02s |
| MedScribe | N/A | N/A | 2m54s | 18.99s |
| GPQA Diamond | N/A | N/A | 2m02s | 13.85s |
| MMLU Pro | N/A | N/A | 46.18s | 4.82s |
| MMMU Pro | N/A | N/A | 111.94s | 7.80s |
| SAGE | N/A | N/A | 3m49s | 10.75s |
| Code Migration | $4.78 | $0.53 | 29m50s | 22m02s |
| LiveCodeBench | N/A | N/A | 7m56s | 21.08s |
| ProgramBench | N/A | N/A | 33m01s | 7m15s |
| SWE-bench | $0.87 | $0.31 | 7m04s | 7m20s |
| Vibe Code Bench v1.1 | $5.45 | $0.83 | 38m10s | 8m22s |
Results available only for Qwen 3.6 Plus
None.
Results available only for Gemini 3.5 Flash Lite
- CyberBench v1.1
- Public Benefits Bench v1.1