Model comparison
Gemini 3.7 Flash vs Hy4 preview
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 45.3 on the Noometry Index.
Last verified . 3 shared benchmarks.
Google
TencentSummary
- They share 3 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 3 categories and Hy4 preview in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 31.9.
- The biggest single-benchmark swing is NYT Connections (extended): 94% for Gemini 3.7 Flash and 68.2% for Hy4 preview.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.7 Flash | Hy4 preview | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 59.8 | 45.3 |
| Released | 2026-08-13 | 2026-08-28 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 64K |
| Input $ / M tokens | $0.75 | $0.75 |
| Output $ / M tokens | $3.75 | $2.25 |
| Results tracked | 44 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Gemini 3.7 Flash: 56.2 (#22), Hy4 preview: 51.6 (#38)
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| LMArena WebDev | 1592 | 1632 |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| FrontierSWE | 20.3% | — |
| SciCode | 59.8% | — |
| LMArena Coding | 1497 | — |
| ALE-Bench | 904.3 | — |
Agentic & Tool Use Not comparable
Gemini 3.7 Flash: 42.1 (#19), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| APEX-Agents | 67.8% | — |
| Remote Labor Index | 5% | — |
| GDP.pdf | 23.8% | — |
Reasoning Gemini 3.7 Flash leads
Gemini 3.7 Flash: 70.0 (#15), Hy4 preview: 31.9 (#79)
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | 94% | 68.2% |
| ARC-AGI-2 | 84.6% | — |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 14.3% | — |
| Chess Puzzles | 47% | — |
| LMArena Hard Prompts | 1494 | — |
| Mystery Game Puzzles | 37% | — |
| DTBench | 96.8% | — |
| LMCA | 50.4% | — |
| Epoch Capabilities Index | 157.27 | — |
Math Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.6 (#23), Hy4 preview: 55.7 (#42)
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| ProofBench | 58% | 75% |
| FrontierMath (Tiers 1-3) | 71.6% | — |
| FrontierMath Tier 4 | 36.6% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| LMArena Math | 1507 | — |
Knowledge Not comparable
Gemini 3.7 Flash: 69.7 (#5), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| GPQA Diamond | 94.8% | — |
| SimpleQA Verified | 69.2% | — |
| LMArena Expert | 1508 | — |
Multimodal Not comparable
Gemini 3.7 Flash: 37.3 (#73), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| LMArena Vision | 1316 | — |
| Furniture Assembly | 26.7% | — |
Multilingual Not comparable
Gemini 3.7 Flash: 57.6 (#7), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1484 | — |
| LMArena Chinese | 1548 | — |
| LMArena French | 1505 | — |
| LMArena German | 1498 | — |
| LMArena Japanese | 1512 | — |
| LMArena Korean | 1483 | — |
| LMArena Russian | 1516 | — |
| LMArena Spanish | 1503 | — |
Instruction Following Not comparable
Gemini 3.7 Flash: 77.7 (#15), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1483 | — |
Long Context Not comparable
Gemini 3.7 Flash: 45.7 (#30), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1492 | — |
Writing & Preference Not comparable
Gemini 3.7 Flash: 71.2 (#20), Hy4 preview: —
| Benchmark | Gemini 3.7 Flash | Hy4 preview |
|---|---|---|
| LMArena Text | 1486 | — |
| LMArena Creative Writing | 1490 | — |
| EQ-Bench Creative Writing | 1723 | — |
| LMArena Multi-Turn | 1489 | — |
Frequently asked questions
Is Gemini 3.7 Flash better than Hy4 preview?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 45.3 on the Noometry Index.
Which is cheaper, Gemini 3.7 Flash or Hy4 preview?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.
Is Gemini 3.7 Flash or Hy4 preview better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 51.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.7 Flash and Hy4 preview share?
3 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Hy4 preview has 3.