# GPT-5 Pro vs Qwen3-1.7B

> GPT-5 Pro is the stronger model overall, scoring 46.4 to 26.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-pro-vs-qwen3-1-7b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where GPT-5 Pro leads 56.7 to 19.6.
- Qwen3-1.7B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Pro | Qwen3-1.7B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 46.4 | 26.6 |
| Rank | 64 | 336 |
| Context | 400K | — |
| Input $/M | $15 | — |
| Output $/M | $120 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Pro: 44.0 (#80)
- Qwen3-1.7B: —

| Benchmark | GPT-5 Pro | Qwen3-1.7B |
|---|---|---|
| WeirdML | 60.4% | — |
| AlgoTune | 1.31 | — |

## Agentic & Tool Use

- GPT-5 Pro: —
- Qwen3-1.7B: 24.7 (#115)

| Benchmark | GPT-5 Pro | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |

## Reasoning

- GPT-5 Pro: 38.9 (#62)
- Qwen3-1.7B: 19.2 (#267)

| Benchmark | GPT-5 Pro | Qwen3-1.7B |
|---|---|---|
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| Kagi LLM Benchmark | 76.8% | — |
| ARC-AGI-1 | 70.2% | — |
| Chess Puzzles | — | 0% |
| EnigmaEval | 18.8% | — |
| Epoch Capabilities Index | 150.28 | — |

## Math

- GPT-5 Pro: 48.5 (#63)
- Qwen3-1.7B: 16.3 (#294)

| Benchmark | GPT-5 Pro | Qwen3-1.7B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 19.5% | — |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- GPT-5 Pro: 56.7 (#42)
- Qwen3-1.7B: 19.6 (#278)

| Benchmark | GPT-5 Pro | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
| Humanity's Last Exam | 31.6% | — |

## FAQ

### Is GPT-5 Pro better than Qwen3-1.7B?

GPT-5 Pro is the stronger model overall, scoring 46.4 to 26.6 on the Noometry Index.

### How many benchmarks do GPT-5 Pro and Qwen3-1.7B share?

0 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Qwen3-1.7B has 4.