Across 15 comparable benchmarks, Mistral Large 4 has better reported results on 13 and worse on 2.
Strong evidence15 of 15 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Mistral Large 4 | Gemini 3.5 Flash-Lite |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $0.700 | $0.300 |
| Output / 1M | $2.10 | $2.50 |
| Blended (4:1) | $0.526 | $0.546 |
| Status | Preview | Available |
| Released | October 6, 2026 | July 21, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 11 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Mistral Large 4 ahead on 3 of 3 counted
Mistral Large 4 ahead on 2 of 2 counted
Split 1–1 of 2 counted
Gemini 3.5 Flash-Lite ahead on 1 of 1 counted
Mistral Large 4 ahead on 5 of 5 counted
No shared comparable results for Abstract reasoning, Computer & tool use, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Mistral Large 4 relative to Gemini 3.5 Flash-Lite. Reading the results
| Benchmark | Mistral Large 4 | Gemini 3.5 Flash-Lite | Gap |
|---|---|---|---|
| Code MigrationMaintenance & Optimization · Hidden-test pass rate (%) | 30.6Thinking High · tools | 6.2Thinking High · tools | +24.4 pts#43 vs #71 of 79 |
| Terminal-Bench 4.0Agentic Development · Resolution rate (%) | 28.3Thinking · tools | 1.0Thinking · tools | +27.3 pts#40 vs #77 of 90 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 78.4Thinking High · tools | 37.2Thinking High · tools | +41.2 pts#36 vs #75 of 121 |
| FrontierMath Tier 4 v2Mathematics · Accuracy (verification_code) | 26.8Thinking High · tools | 0.0Thinking High · tools | +26.8 pts#40 vs #71 of 73 |
| FrontierMath v2Mathematics · Accuracy (verification_code) | 58.6Thinking High · tools | 26.0Thinking High · tools | +32.6 pts#46 vs #74 of 85 |
| MedCodeClinical Workflows · Accuracy (%) | 40.7Thinking High · no tools | 43.5≠Thinking High · tools | −2.8 pts#58 vs #42 of 97 |
| MedScribeClinical Workflows · Rubric pass rate (%) | 80.4Thinking High · no tools | 70.9≠Thinking High · tools | +9.5 pts#53 vs #85 of 99 |
| MMMU-ProVisual Understanding · Accuracy | 76.4Thinking · no tools | 79.0Thinking · no tools | −2.6 pts#55 vs #38 of 136 |
| EMB (Excel Modeling)Finance · Accuracy (%) | 56.2Thinking High · tools | 43.2Thinking High · tools | +13.0 pts#49 vs #62 of 78 |
| Finance Agent v2Finance · Score | 54.7Thinking High · tools | 47.4Thinking High · tools | 1.15×#24 vs #51 of 75 |
| Harvey's Legal Agent BenchmarkLegal · Accuracy (%) | 15.8Thinking High · tools | 0.0Thinking High · tools | +15.8 pts#6 vs #44 of 52 |
| Legal Research BenchLegal · Score | 31.7Thinking High · tools | 13.9Thinking High · tools | 2.28×#52 vs #78 of 91 |
| Tax Agent BenchFinance · Accuracy (%, rubric × citation quality) | 63.3Thinking High · tools | 7.3Thinking High · tools | +56.0 pts#14 vs #70 of 74 |
| AA Intelligence Index v5.0.1Capability Indices · Index (0-100) | 25.3Thinking · tools | 11.7≠Thinking High · tools | 2.17×#39 vs #53 of 62 |
| LiveBenchCross-capability Suites · Accuracy | 71.8Thinking High · no tools | 63.9Thinking High · no tools | +7.9 pts#53 vs #73 of 106 |
Maintenance & Optimization · Hidden-test pass rate (%)
Agentic Development · Resolution rate (%)
Code Generation & Editing · Pass rate (%)
Mathematics · Accuracy (verification_code)
Mathematics · Accuracy (verification_code)
Visual Understanding · Accuracy
Finance · Accuracy (%)
Finance · Score
Legal · Accuracy (%)
Legal · Score
Finance · Accuracy (%, rubric × citation quality)
Capability Indices · Index (0-100)
Cross-capability Suites · Accuracy
A dash means no result is available.
| Benchmark | Mistral Large 4 | Gemini 3.5 Flash-Lite |
|---|---|---|
| GPQA Diamond | — | 83.3 |
| MysteryMechanism | 12.2 | — |
| ProofBench v1.1 (Lean 4) | 10.0 | — |
| Riemann-bench | — | 11.2 |
| SciCode | — | 41.3 |
| AA Cyber Index | 49.5 | — |
| APEX-SWE | — | 31.2 |
| DeepSWE | 61.7 | — |
| FrontierCode 1.1 | 39.4 | — |
| FrontierCode 2.0 | 8.8 | — |
| IOI (Vals v2) | 45.3 | — |
| SWE-Atlas-QnA | 59.4 | — |
| SWE-Bench Pro - Public | — | 54.2 |
| SWE-sweep | — | 0.12 |
| Terminal-Bench 2.1 | — | 54.0 |
| Terminal-Bench 4.1 | 27.6 | — |
| Vibe Code Bench 1-100 | 14.3 | — |
| WeirdML v3 | 0.044 | — |
| APEX-Agents | — | 29.3 |
| OSWorld-Verified | — | 74.0 |
| Toolathlon-Verified | — | 57.1 |
| ECI | — | 145 |
| LiveBench 2.0 | 47.7 | — |
| Vals Index | — | 36.7 |
| Vals Index v2.1 | 48.0 | — |
| Creative Writing | — | 1559 |
| Context Arena | — | 72.6 |
| GDP.pdf | — | 13.6 |
| AutomationBench | — | 4.0 |
| Public Benefits Bench v1.1 | — | 51.8 |
| SAGE | — | 47.3 |
| τ³-Banking | — | 17.5 |
| ARC-AGI-1 | — | 53.5 |
| ARC-AGI-2 | — | 10.3 |
| BioMysteryBench | 67.0 | — |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
Mistral Large 4 costs3.5%lessthan Gemini 3.5 Flash-Lite per million tokens.Using standard rates at this token mix.
Mistral Large 4: Standard pricing. Mistral official pricing (docs.mistral.ai/inference/pricing) verified 2026-11-13; price reduced from $1.36 Mistral official pricing (docs.mistral.ai/inference/pricing) verified 2026-11-13; price reduced from $4.18
Gemini 3.5 Flash-Lite: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-10-21; paid tier; standard tier
| Price / 1M tokens | Mistral Large 4 | Gemini 3.5 Flash-Lite | Ratio |
|---|---|---|---|
| Input | $0.70 | $0.30 | 2.33× |
| Output | $2.10 | $2.50 | 0.84× |
| Cached input | $0.07 | $0.03 | 2.33× |
| Cache write | — | — | — |
| Blended | $0.526 | $0.546 | 0.96× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
Mistral Large 4 relative to Gemini 3.5 Flash-Lite
Summary: 2 of 2 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 2 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Mistral Large 4 33.4× more expensive
Mistral Large 4 6.1× more expensive
Mistral Large 4 33.4× more expensive
Mistral Large 4 6.1× more expensive
Effort, protocol, aggregation and source match; other run conditions may differ.
Mistral Large 4
Gemini 3.5 Flash-Lite
Effort, protocol, aggregation and source match; other run conditions may differ.
Mistral Large 4
Gemini 3.5 Flash-Lite
| Benchmark | Mistral Large 4 | Gemini 3.5 Flash-Lite |
|---|---|---|
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | $0.139 / task Average · ARC-AGI-2 Score: 10.3 Thinking High (With Tools) $0.0437 / task Average · ARC-AGI-2 Score: 5.3 Thinking Medium (With Tools) |
| AutomationBench | Not reported | $0.13 / task Average · Pass Rate: 3.4 Thinking High (With Tools) · zapier-private-heldout $0.12 / task Average · Pass Rate: 4.0 Thinking Medium (With Tools) · zapier-private-heldout |
| BioMysteryBench | Not reported | |
| Code Migration | Not reported | |
| EMB (Excel Modeling) | Not reported | |
| Finance Agent v2 | Not reported | |
| FrontierCode 2.0 | Not reported | |
| Harvey's Legal Agent Benchmark | Not reported | |
| IOI (Vals v2) | Not reported | |
| Legal Research Bench | Not reported | |
| LiveBench 2.0 | $0.6726 / task Average · Overall score (equal-weight mean of 7 suite scores, 0-100): 47.7 Thinking High (With Tools) | Not reported |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| MysteryMechanism | Not reported | |
| ProofBench v1.1 (Lean 4) | Not reported | |
| SWE-sweep | Not reported | |
| Terminal-Bench 4.0 | $2.73 / task Average · Resolution rate (%): 26.3 Unspecified Reasoning (With Tools) · vals-mini-swe | Not reported |
| Terminal-Bench 4.1 | Not reported | |
| Vals Index v2.1 | Not reported | |
| Vibe Code Bench 1-100 | Not reported | |
| Vibe Code Bench v1.1 | Not reported | |
| WeirdML v3 | $28.7748 / task Average · Official score (0-1; higher is better): 0.044 Thinking High (With Tools) | Not reported |
| Attribute | Mistral Large 4 | Gemini 3.5 Flash-Lite |
|---|---|---|
| Availability | Preview | Available |
| Provider | MistralAI | Google Deep Mind |
| Model type | Multimodal model | Multimodal model |
| First release | October 6, 2026 | July 21, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | — | 64K tokens |
| Total parameters | 1.1T | — |
| Active parameters | 49B | — |
| Architecture | Mixture of Experts (MoE) | Undisclosed |
| Documented capabilities | Reasoning, Multilingual, Function calling, Tool use, Structured output, Long context, Coding | Reasoning, Coding, Translation, Function calling, Tool use, Structured output, Web search, Long context |
| Input modalities | Text, Image | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Mistral Large 4 or Gemini 3.5 Flash-Lite? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.