# GPT-5 vs Hy3

> GPT-5 is the stronger model overall, scoring 50.9 to 43.6 on the Noometry Index. Hy3 costs 15× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GPT-5 scores higher in 6 categories and Hy3 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 44.1.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.25 / $10 for GPT-5.
- GPT-5 accepts more context: 400K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 | Hy3 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 50.9 | 43.6 |
| Rank | 37 | 79 |
| Context | 400K | 262K |
| Input $/M | $1.25 | $0.13 |
| Output $/M | $10 | $0.53 |
| Weights | Proprietary | Open |

## Coding

- GPT-5: 50.7 (#39)
- Hy3: 46.6 (#60)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena WebDev | 1417 | 1509 |
| LMArena Coding | 1436 | 1465 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| SciCode | 42.9% | — |
| GSO | 6.9% | — |
| WeirdML | 60.7% | — |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |

## Agentic & Tool Use

- GPT-5: 33.0 (#53)
- Hy3: —

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |

## Reasoning

- GPT-5: 38.3 (#55)
- Hy3: 25.0 (#134)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1449 |
| ARC-AGI-2 | 9.9% | — |
| SimpleBench | 56.7% | — |
| Kagi LLM Benchmark | 72.7% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 65.7% | — |
| CritPt | 12.6% | — |
| Chess Puzzles | 37% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| Mystery Game Puzzles | 23% | — |
| DTBench | 90.7% | — |
| LMCA | 40% | — |
| Epoch Capabilities Index | 150 | — |
| ForecastBench | 61.4 | — |

## Math

- GPT-5: 54.6 (#36)
- Hy3: 37.4 (#98)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Math | 1406 | 1475 |
| FrontierMath (Tiers 1-3) | 55.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 18% | — |
| Omni-MATH | 64.7% | — |
| MATH Level 5 | 98.1% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GPT-5: 56.5 (#37)
- Hy3: 40.2 (#108)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Expert | 1420 | 1461 |
| GPQA Diamond | 86.2% | — |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |

## Multimodal

- GPT-5: 46.1 (#12)
- Hy3: —

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Vision | 1232 | — |
| GeoBench | 81% | — |
| VPCT | 66% | — |

## Multilingual

- GPT-5: 51.5 (#105)
- Hy3: 53.7 (#60)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1397 | 1427 |
| LMArena Chinese | 1423 | 1496 |
| LMArena French | 1409 | 1461 |
| LMArena Korean | 1361 | 1390 |
| LMArena Russian | 1406 | 1435 |
| LMArena Spanish | 1398 | 1448 |
| LMArena German | 1415 | — |
| LMArena Japanese | 1411 | — |

## Instruction Following

- GPT-5: 74.0 (#107)
- Hy3: 75.3 (#68)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1388 | 1425 |
| IFEval | 87.5% | — |

## Long Context

- GPT-5: 69.5 (#2)
- Hy3: 44.1 (#70)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1399 | 1443 |
| Fiction.LiveBench | 97.2% | — |

## Writing & Preference

- GPT-5: 63.5 (#63)
- Hy3: 62.5 (#75)

| Benchmark | GPT-5 | Hy3 |
|---|---|---|
| LMArena Text | 1406 | 1442 |
| LMArena Creative Writing | 1365 | 1399 |
| LMArena Multi-Turn | 1426 | 1436 |
| Short-Story Creative Writing | 86% | — |
| EQ-Bench Creative Writing | 1627 | — |
| WildBench | 85.7% | — |

## FAQ

### Is GPT-5 better than Hy3?

GPT-5 is the stronger model overall, scoring 50.9 to 43.6 on the Noometry Index. Hy3 costs 15× less per token, which makes it the better buy when GPT-5's lead doesn't matter for your workload.

### Which is cheaper, GPT-5 or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; GPT-5 lists at $1.25 and $10.

### Is GPT-5 or Hy3 better for coding?

GPT-5 scores higher on coding benchmarks: 50.7 versus 46.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 does, with 400K tokens against 262K.

### How many benchmarks do GPT-5 and Hy3 share?

16 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and Hy3 has 17.