Gemini 3.7 Flash
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Shogo Agent Index
Estimated#23 of 9255.7range 44.2–67.1 · 24% of weight measured
Agentic coding
61
31% measured
Long-horizon autonomy
64
estimated
Knowledge-work agents
48
52% measured
Computer use
43
estimated
Security & context learning
53
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 81 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 82 | |
| DeepSWE | 65.5% | 6% | mini-swe-agent · $2.03/task | |
| FrontierSWE | 20.3% | 5% | proximus · $34.14/task | |
| CursorBench | est. | 4% | predicted 42 | |
| GSO-Bench | est. | 4% | predicted 41 | |
| METR Time Horizons | est. | 10% | predicted 79 | |
| Vending-Bench 2 | est. | 6% | predicted 64 | |
| PostTrainBench | est. | 4% | predicted 28 | |
| APEX-Agents | 67.8% | 8% | source | |
| GDPval | est. | 7% | predicted 54 | |
| Remote Labor Index | 5.0% | 5% | source | |
| DeepResearch Bench | est. | 5% | predicted 49 | |
| OSWorld 2.0 | est. | 6% | predicted 15 | |
| OSWorld | est. | 4% | predicted 84 | |
| Cybench | est. | 5% | predicted 82 | |
| CL-bench | est. | 5% | predicted 24 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 95.5% | source |
| ARC-AGI-2 | Reasoning | 84.6% | source |
| Chess Puzzles | Reasoning | 66.0% | source |
| CritPt | Reasoning | 14.3% | source |
| DTBench | Knowledge | 96.8% | source |
| FrontierCode | Coding | 43.6% | devin-cli |
| FrontierMath Tiers 1-3 | Math | 71.6% | source |
| FrontierMath Tier 4 | Math | 36.6% | source |
| GPQA Diamond | Reasoning | 94.8% | source |
| LMCA | Knowledge | 50.4% | source |
| MirrorCode | Coding | 41.1% | source |
| OTIS Mock AIME | Math | 97.2% | source |
| ProofBench | Math | 58.0% | source |
| SciCode | Coding | 59.8% | source |
| SimpleQA Verified | Knowledge | 69.2% | source |
| WebDev Arena | Coding | 1587 | source |
API hosts
Live prices and uptime for every host serving Gemini 3.7 Flash via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| $0.38 | $1.88 | $0.037 | $0.17 | 31.2% | — | |
| Google AI Studio | $0.38 | $1.88 | $0.037 | $0.17 | 100.0% | — |
| $0.75 | $3.75 | $0.075 | $0.35 | 100.0% | — | |
| Google AI Studio | $0.75 | $3.75 | $0.075 | $0.35 | 100.0% | — |
| $1.35 | $6.75 | $0.14 | $0.62 | 99.9% | — | |
| Google AI Studio | $1.35 | $6.75 | $0.14 | $0.62 | 100.0% | — |