Up to four models
GPT-5.4 Nano vs Qwen3.6 27B
On the index (GPT-4 = 100), GPT-5.4 Nano scores 141 and Qwen3.6 27B 141. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.4 Nano
141125–157
WeightsClosed
ReleasedMar 2026
Price in / out$0.20 / $1.25
Context400K
Core tests taken4 of 9
141125–158
WeightsOpen
ReleasedApr 2026
Price in / out$0.32 / $3.2
Context262K
Core tests taken2 of 9
GPT-5.4 Nano and Qwen3.6 27B are too close to call (0 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 2.2× less.
Test by testthird-party results
GPT-5.4 Nano
Qwen3.6 27B
Every result as a table
| Test | GPT-5.4 Nano | Qwen3.6 27B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 78.5% | 85.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 44.9% | 35.1% |
| AIME-style maths (OTIS mock) | 87.8% | 91.1% |
| Coding | ||
| SWE-bench | 69.8% | 70.0% |
| Vibe Code Bench v1.1 | 26.1% | 11.9% |
| Agents | ||
| DTBench | 80.3% | 78.1% |
| LMCA | 36.9% | 34.5% |
| Mystery game puzzles | 9.0% | 7.0% |
| Professional work | ||
| CorpFin v2 | 61.2% | 62.3% |
| MortgageTax | 59.1% | 68.3% |
| TaxEval v2 | 67.4% | 71.3% |
Tests at least two of these models have taken. Bold rows are the core tests.