Model comparison
Gemini 3.1 Flash Lite vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 44.6 to 40.4 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.2× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Google
TencentSummary
- They share 2 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 0 categories and Hy4 preview in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 54.5 to 39.5.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 68.2% for Hy4 preview.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Hy4 preview | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 40.4 | 44.6 |
| Released | 2026-03-03 | 2026-08-28 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 64K |
| Input $ / M tokens | $0.25 | $0.83 |
| Output $ / M tokens | $1.50 | $2.50 |
| Results tracked | 38 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Gemini 3.1 Flash Lite: 37.5 (#179), Hy4 preview: 51.4 (#36)
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| LMArena WebDev | 1256 | 1633 |
| SciCode | 41.9% | — |
| WeirdML | 52.2% | — |
| LMArena Coding | 1400 | — |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 29.9 (#72), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
Reasoning Hy4 preview leads
Gemini 3.1 Flash Lite: 22.3 (#181), Hy4 preview: 30.6 (#75)
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | 8.2% | 68.2% |
| Kagi LLM Benchmark | 67.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| LMArena Hard Prompts | 1407 | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| Epoch Capabilities Index | 144.45 | — |
| ForecastBench | 54.4 | — |
Math Hy4 preview leads
Gemini 3.1 Flash Lite: 39.5 (#82), Hy4 preview: 54.5 (#37)
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| ProofBench | — | 75% |
| LMArena Math | 1427 | — |
Knowledge Not comparable
Gemini 3.1 Flash Lite: 41.7 (#95), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 8.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| LMArena Expert | 1397 | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 38.7 (#57), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Not comparable
Gemini 3.1 Flash Lite: 52.5 (#82), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1410 | — |
| LMArena Chinese | 1461 | — |
| LMArena French | 1423 | — |
| LMArena German | 1429 | — |
| LMArena Japanese | 1411 | — |
| LMArena Korean | 1393 | — |
| LMArena Russian | 1420 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Not comparable
Gemini 3.1 Flash Lite: 72.9 (#126), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1376 | — |
Long Context Not comparable
Gemini 3.1 Flash Lite: 42.5 (#117), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1394 | — |
Writing & Preference Not comparable
Gemini 3.1 Flash Lite: 61.0 (#90), Hy4 preview: —
| Benchmark | Gemini 3.1 Flash Lite | Hy4 preview |
|---|---|---|
| LMArena Text | 1416 | — |
| LMArena Creative Writing | 1401 | — |
| LMArena Multi-Turn | 1417 | — |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 44.6 to 40.4 on the Noometry Index. Gemini 3.1 Flash Lite costs 2.2× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or Hy4 preview?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is Gemini 3.1 Flash Lite or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.1 Flash Lite and Hy4 preview share?
2 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Hy4 preview has 3.