# GPT-4.1 mini vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.5 to 33.6 on the Noometry Index. GPT-4.1 mini costs 5.4× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4-1-mini-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 24.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 6.7% for GPT-4.1 mini and 64.6% for Qwen3.7 Max.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.6 | 51.5 |
| Rank | 240 | 42 |
| Context | 1.05M | 1M |
| Input $/M | $0.40 | $2.50 |
| Output $/M | $1.60 | $7.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.1 mini: 30.6 (#293)
- Qwen3.7 Max: 50.4 (#45)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| SciCode | 40.4% | 48.8% |
| LMArena Coding | 1367 | 1498 |
| SWE-bench Verified | — | 77.3% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1515 |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- GPT-4.1 mini: 33.3 (#55)
- Qwen3.7 Max: 22.1 (#135)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| GBAEval | — | 0.4% |

## Reasoning

- GPT-4.1 mini: 10.8 (#340)
- Qwen3.7 Max: 49.2 (#38)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| CritPt | 0% | 13.4% |
| Chess Puzzles | 7% | 19% |
| LMArena Hard Prompts | 1349 | 1483 |
| Mystery Game Puzzles | 7% | 32% |
| DTBench | 68.8% | 92.3% |
| LMCA | 21.1% | 44% |
| Epoch Capabilities Index | 135.01 | 153.68 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 48.6% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 3.5% | — |
| EBR-Bench | — | 9.5% |

## Math

- GPT-4.1 mini: 24.1 (#270)
- Qwen3.7 Max: 62.4 (#32)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 64.6% |
| OTIS Mock AIME 2024-2025 | 44.7% | 95.6% |
| LMArena Math | 1343 | 1490 |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |

## Knowledge

- GPT-4.1 mini: 34.7 (#194)
- Qwen3.7 Max: 61.6 (#28)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 65.8% | 90.9% |
| SimpleQA Verified | 12.7% | 55.8% |
| LMArena Expert | 1338 | 1488 |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |

## Multimodal

- GPT-4.1 mini: 35.8 (#82)
- Qwen3.7 Max: —

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1181 | — |

## Multilingual

- GPT-4.1 mini: 45.7 (#166)
- Qwen3.7 Max: 56.9 (#15)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1318 | 1474 |
| LMArena Chinese | 1329 | 1530 |
| LMArena Russian | 1324 | 1484 |
| LMArena French | 1358 | — |
| LMArena German | 1351 | — |
| LMArena Japanese | 1290 | — |
| LMArena Korean | 1298 | — |
| LMArena Spanish | 1319 | — |

## Instruction Following

- GPT-4.1 mini: 73.7 (#118)
- Qwen3.7 Max: 76.7 (#38)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1333 | 1460 |
| IFEval | 90.4% | — |

## Long Context

- GPT-4.1 mini: 31.8 (#275)
- Qwen3.7 Max: 45.4 (#40)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1344 | 1482 |
| Fiction.LiveBench | 44.4% | — |

## Writing & Preference

- GPT-4.1 mini: 48.6 (#199)
- Qwen3.7 Max: 65.0 (#54)

| Benchmark | GPT-4.1 mini | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1340 | 1476 |
| LMArena Creative Writing | 1300 | 1449 |
| LMArena Multi-Turn | 1354 | 1481 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is GPT-4.1 mini better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 33.6 on the Noometry Index. GPT-4.1 mini costs 5.4× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

### Which is cheaper, GPT-4.1 mini or Qwen3.7 Max?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

### Is GPT-4.1 mini or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 30.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 1M.

### How many benchmarks do GPT-4.1 mini and Qwen3.7 Max share?

23 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Qwen3.7 Max has 33.