Gemini 3.5 Flash vs Mistral Large 4
| Spec | Gemini 3.5 Flash | Mistral Large 4 |
|---|---|---|
| Respan Index | 44.4 (#48) | 45.0 (#47) |
| Blended price per 1M | $1.69 | $1.05 |
| Context window | 1.0M | 1M |
| Input / output per 1M | $0.75 / $4.5 | $0.7 / $2.1 |
| Max output | 66K | - |
| Input | text, vision, audio | text, vision |
| Released | 2026-05-19 | 2026-10-06 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Gemini 3.5 Flash | Mistral Large 4 |
|---|---|---|
| Coding | 19.4 Gemini 3.5 Flash | 41.5 Mistral Large 4 |
| Agents | 49.8 Gemini 3.5 Flash | 56.0 Mistral Large 4 |
| Reasoning | 50.1 Gemini 3.5 Flash | 42.7 Mistral Large 4 |
| Knowledge & language | 65.7 Gemini 3.5 Flash | 18.2 Mistral Large 4 |
| Human preference | 53.5 Gemini 3.5 Flash | 54.3 Mistral Large 4 |
Benchmarks both report
Gemini 3.5 Flash leads on 10 of the 19 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Gemini 3.5 Flash | Mistral Large 4 |
|---|---|---|
| Chess Puzzles (Epoch AI) | 45% | 33% |
| LMArena Elo | 1478 | 1432 |
| LMArena WebDev (LMArena) | 1499 | 1544 |
| LMArena Vision (LMArena) | 1282 | 1252 |
| APEX-Agents (Mercor) | 27.5% | 51.6% |
| FrontierMath Tier 4 v2 (Epoch AI) | 26.8% | 26.8% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 62.8% | 58.6% |
| GPQA Diamond | 92.8% | 88.1% |
| LiveBench Agentic Coding (LiveBench) | 49% | 57.2% |
| LiveBench Coding (LiveBench) | 78.2% | 77.2% |
| LiveBench Data Analysis (LiveBench) | 64.9% | 76.5% |
| LiveBench Instruction Following (LiveBench) | 75.6% | 64.8% |
| LiveBench Language (LiveBench) | 84.6% | 49.6% |
| LiveBench Mathematics (LiveBench) | 88.2% | 93.6% |
| LiveBench Reasoning (LiveBench) | 82% | 83.9% |
| Mystery Game Puzzles (Epoch AI) | 32% | 17% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 95.6% | 98.3% |
| SimpleQA Verified | 66.2% | 20% |
| Terminal-Bench 4.0 (Vals AI) | 6.1% | 27.8% |
FAQ
Is Gemini 3.5 Flash better than Mistral Large 4?
Mistral Large 4 scores 45.0 on the Respan Index (#47), ahead of Gemini 3.5 Flash at 44.4 (#48). Gemini 3.5 Flash leads on 10 of the 19 benchmarks both report.
Which is cheaper, Gemini 3.5 Flash or Mistral Large 4?
Gemini 3.5 Flash lists at $0.75 input and $4.5 output per 1M tokens; Mistral Large 4 at $0.7 and $2.1. Mistral Large 4 is 1.6x cheaper per token at list price.
Which has the larger context window?
Gemini 3.5 Flash accepts 1.0M tokens and Mistral Large 4 1M tokens.