Gemini 3.5 Flash vs Mistral Large 4: Benchmark Comparison
Gemini 3.5 Flash has the higher score on 2 of 7 shared benchmarks; Mistral Large 4 leads on 5.
The largest observed score gap is 29.72 pts on Vibe Code Bench v1.1 , where Mistral Large 4 leads.
Reported ±1 standard-error ranges overlap on 2 of 7 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 | Gemini 3.5 Flash | Mistral Large 4 | Gap | Reported uncertainty |
|---|---|---|---|---|
| Legal Research Bench | 30.77% ±3.21 | 31.73% ±3.23 | 0.96 pts | Reported ±1 SE ranges overlap |
| Tax Agent Bench | 21.65% ±2.96 | 30.39% ±3.31 | 8.74 pts | Reported ±1 SE ranges do not overlap |
| MedCode | 55.83% ±2.11 | 40.69% ±2.17 | 15.14 pts | Reported ±1 SE ranges do not overlap |
| MedScribe | 76.57% ±1.92 | 80.43% ±2.00 | 3.86 pts | Reported ±1 SE ranges overlap |
| ProofBench v1.1 | 31.00% ±4.65 | 10.00% ±3.02 | 21.00 pts | Reported ±1 SE ranges do not overlap |
| Terminal-Bench 4.0 | 6.06% ±1.51 | 27.78% ±1.82 | 21.72 pts | Reported ±1 SE ranges do not overlap |
| Vibe Code Bench v1.1 | 48.68% ±4.73 | 78.40% ±3.55 | 29.72 pts | Reported ±1 SE ranges do not overlap |
Performance by category
| Category | Gemini 3.5 Flash average | Mistral Large 4 average |
|---|---|---|
| Legal | 30.77% | 31.73% |
| Finance | 21.65% | 30.39% |
| Healthcare | 66.20% | 60.56% |
| Math | 31.00% | 10.00% |
| Coding | 27.37% | 53.09% |
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 | Gemini 3.5 Flash cost | Mistral Large 4 cost | Gemini 3.5 Flash latency | Mistral Large 4 latency |
|---|---|---|---|---|
| Legal Research Bench | $1.31 | $5.33 | 4m38s | 1h33m |
| Tax Agent Bench | $0.86 | $2.72 | 3m53s | 57m18s |
| MedCode | N/A | N/A | 25.29s | 68.68s |
| MedScribe | N/A | N/A | 57.08s | 2m05s |
| ProofBench v1.1 | $0.57 | $0.64 | 6m34s | 20m59s |
| Terminal-Bench 4.0 | $5.98 | $10.25 | 1h11m | 1h40m |
| Vibe Code Bench v1.1 | $2.54 | $39.46 | 14m53s | 2h53m |
Results available only for Gemini 3.5 Flash
- LegalBench
- MortgageTax
- TaxEval v2
- Terminal-Bench-Science
- GPQA Diamond
- MMLU Pro
- MMMU Pro
- SAGE
- LiveCodeBench
- ProgramBench
- SkillsBench
- SWE-bench
- Public Benefits Bench v1.1
Results available only for Mistral Large 4
- Vals Finance Index
- Vals Legal Index
- HLAB-Vals-1.1
- EMB v1.1
- Finance Agent v2.1
- BioMysteryBench
- MysteryMechanism
- IOI
- SWE-bench Multimodal
- Vibe Code Bench 1-100