# GPT-4.1 mini vs Hy3

> Hy3 is the stronger model overall, scoring 44.2 to 33.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-hy3
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 30.6.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 mini | Hy3 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 33.6 | 44.2 |
| Rank | 240 | 79 |
| Context | 1.05M | 262K |
| Input $/M | $0.40 | $0.13 |
| Output $/M | $1.60 | $0.53 |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1 mini: 30.6 (#293)
- Hy3: 46.8 (#63)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Coding | 1367 | 1464 |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1508 |
| SciCode | 40.4% | — |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |

## Agentic & Tool Use

- GPT-4.1 mini: 33.3 (#55)
- Hy3: —

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |

## Reasoning

- GPT-4.1 mini: 10.8 (#340)
- Hy3: 26.1 (#136)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1349 | 1447 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 3.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 7% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 21.1% | — |
| Epoch Capabilities Index | 135.01 | — |

## Math

- GPT-4.1 mini: 24.1 (#270)
- Hy3: 40.1 (#93)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Math | 1343 | 1475 |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| OTIS Mock AIME 2024-2025 | 44.7% | — |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |

## Knowledge

- GPT-4.1 mini: 34.7 (#194)
- Hy3: 40.8 (#114)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Expert | 1338 | 1460 |
| GPQA Diamond | 65.8% | — |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |

## Multimodal

- GPT-4.1 mini: 35.8 (#82)
- Hy3: —

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Vision | 1181 | — |

## Multilingual

- GPT-4.1 mini: 45.7 (#166)
- Hy3: 53.5 (#65)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Non-English | 1318 | 1426 |
| LMArena Chinese | 1329 | 1493 |
| LMArena French | 1358 | 1461 |
| LMArena German | 1351 | 1439 |
| LMArena Japanese | 1290 | 1392 |
| LMArena Korean | 1298 | 1395 |
| LMArena Russian | 1324 | 1432 |
| LMArena Spanish | 1319 | 1456 |

## Instruction Following

- GPT-4.1 mini: 73.7 (#118)
- Hy3: 75.1 (#70)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1333 | 1426 |
| IFEval | 90.4% | — |

## Long Context

- GPT-4.1 mini: 31.8 (#275)
- Hy3: 44.1 (#75)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Longer Query | 1344 | 1442 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-4.1 mini: 48.6 (#199)
- Hy3: 62.2 (#81)

| Benchmark | GPT-4.1 mini | Hy3 |
|---|---|---|
| LMArena Text | 1340 | 1439 |
| LMArena Creative Writing | 1300 | 1402 |
| LMArena Multi-Turn | 1354 | 1436 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |

## FAQ

### Is GPT-4.1 mini better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 33.6 on the Noometry Index.

### Which is cheaper, GPT-4.1 mini or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; GPT-4.1 mini lists at $0.40 and $1.60.

### Is GPT-4.1 mini or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 30.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 262K.

### How many benchmarks do GPT-4.1 mini and Hy3 share?

17 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Hy3 has 19.