Leaderboard / Model
Gemini 3.5 Flash
Google DeepMind · Closed weights · Released May 19, 2026 · $1.50 in · $9 out per 1M tokens
52Overall · rank 16
Score by job
Coding
55 · rank 19 · 3 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| DeepSWE | 37.4% | gemini-3.5-flash_medium | -1.26 |
| SWE-bench Verified | 79.3% | gemini-3.5-flash_high | 0.90 |
| LMArena Coding | 1491 rating | gemini-3.5-flash-high | 0.01 |
Agents
Not enough data · 1 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| APEX-Agents | 27.5% | gemini-3.5-flash_unknown | -2.36 |
Reasoning
69 · rank 12 · 3 of 4 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| GPQA Diamond | 92.8% | gemini-3.5-flash_high | 0.50 |
| ARC-AGI-2 | 72.1% | gemini-3.5-flash_high | 0.37 |
| SimpleBench | 76.7% | gemini-3.5-flash_unknown | 1.13 |
Math
41 · rank 20 · 5 of 5 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 62.8% | gemini-3.5-flash_high | -0.36 |
| FrontierMath Tier 4 | 26.8% | gemini-3.5-flash_high | -0.59 |
| OTIS Mock AIME | 95.6% | gemini-3.5-flash_high | -0.00 |
| ProofBench | 31.0% | gemini-3.5-flash_high | -0.66 |
| LMArena Math | 1505 rating | gemini-3.5-flash-high | 0.92 |
Writing
68 · rank 12 · 2 of 2 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena Creative Writing | 1469 rating | gemini-3.5-flash-high | 0.53 |
| LMArena Instruction Following | 1466 rating | gemini-3.5-flash-high | 0.05 |
Design
28 · rank 35 · 1 of 1 benchmarks
| Benchmark | Result | Variant | z |
|---|---|---|---|
| LMArena WebDev | 1500 rating | gemini-3.5-flash-high | -0.57 |