Gemini 3.7 Flash
| Released | 2026-08-13 |
|---|---|
| Price per 1M | $0.75 in · $3.75 out |
| Overall score | 60.2 · rank 26 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 60.2 | 26 | 40 |
| Overall: Coding | 59.6 | 32 | 27 |
| Overall: Reasoning | 61.9 | 22 | 14 |
| Overall: Agentic work | 60.4 | 28 | 25 |
| Overall: Frontend | 57.9 | 40 | 13 |
| Coding | 59.6 | 29 | 9 |
| Agents | 59.8 | 34 | 9 |
| Reasoning | 64.4 | 16 | 7 |
| Math | 59.3 | 33 | 4 |
| Knowledge | 60.9 | 21 | 3 |
| Frontend | 56.4 | 44 | 2 |
| General | 57.4 | 42 | 4 |
| Multimodal | 62.1 | 6 | 2 |
| Value vs price | +11.2 | 25 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 61.2 ±3.2 | 5 |
| High | 60.1 ±0.7 | 35 |
| Low | 58.2 ±4.1 | 5 |
| Medium | 60.9 ±4.3 | 6 |
Evidence
Coding 59.6 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierSWE | 20.3% | Epoch AI | 2026-11-11 |
| DeepSWE | 65.5% | Epoch AI | 2026-11-11 |
| FrontierCode | 43.6% | Epoch AI | 2026-11-11 |
| MirrorCode | 41.1% | Epoch AI | 2026-10-21 |
| IOI | 67.8% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 80.8% | Vals AI | 2026-09-01 |
| SciCode | 59.8% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 88.7% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 59.8 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 12.4% | Terminal-Bench | 2026-08-13 |
| SRE Bench | 4.6% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 7.1% | Vals AI | 2026-11-09 |
| APEX-Agents | 67.8% | Epoch AI | 2026-11-11 |
| Terminal-Bench 4.0 (Vals run) | 12.1% | Vals AI | 2026-11-09 |
| Remote Labor Index | 5.0% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.1 (Vals run) | 77.5% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 22.8% | Vals AI | 2026-11-09 |
| SkillsBench | 65.9% | Vals AI | 2026-10-29 |
| CyberBench v1.1 | 43.8% | Vals AI | 2026-11-05 |
Reasoning 64.4 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 94.0% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 84.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 84.6% | ARC Prize | 2026-11-11 |
| CritPt | 14.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 95.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 95.5% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 94.8% | Epoch AI | 2026-08-14 |
| GPQA Diamond (Vals run) | 93.9% | Vals AI | 2026-09-01 |
| Chess Puzzles | 66.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 37.0% | Epoch AI | 2026-08-14 |
Math 59.3 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 71.6% | Epoch AI | 2026-08-14 |
| FrontierMath Tier 4 | 36.6% | Epoch AI | 2026-08-14 |
| OTIS Mock AIME 2024-2025 | 97.2% | Epoch AI | 2026-08-14 |
| ProofBench v1.1 | 58.0% | Vals AI | 2026-11-09 |
| ProofBench | 58.0% | Epoch AI | 2026-11-11 |
Knowledge 60.9 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 69.2% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 90.1% | Vals AI | 2026-09-01 |
| Legal Research Bench | 34.6% | Vals AI | 2026-11-09 |
Frontend 56.4 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 70.4% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,588 | LMArena | 2026-11-09 |
General 57.4 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,448 | Lech Mazur | 2026-10-26 |
| EQ-Bench Creative Writing v3 | 1,720 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,489 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 39.0% | Lech Mazur | 2026-10-23 |
Multimodal 62.1 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 89.0% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,294 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 91.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 85.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 91.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 85.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 63.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 52.9% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 63.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 52.9% | ARC Prize | A stronger configuration result was used |
| CritPt | 9.4% | Epoch AI | A stronger configuration result was used |
| CritPt | 5.7% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 65.3% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 53.8% | Epoch AI | A stronger configuration result was used |
| SciCode | 57.2% | Epoch AI | A stronger configuration result was used |
| SciCode | 53.6% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-3-7-flash