Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
1 benchmarks in common.
4 models selected. 1 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | OpenAI | Qwen | Qwen | Qwen |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,447 | 1,394 | Not in our dataset | Not in our dataset |
| LiveBench 1.0General reasoning | 66.4% | Not in our dataset | Not in our dataset | 74.3% |
| GPQA DiamondScientific knowledge | 88.0% | 84.2% | 86.0% | 65.8% |
| HLEAcademic reasoning | 28.2% | 22.4% | 21.4% | Not in our dataset |
| MMLU ProMulti-task understanding | Not in our dataset | 85.3% | 85.2% | Not in our dataset |
| AIME 2025Mathematics | Not in our dataset | Not in our dataset | Not in our dataset | 70.9% |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | 69.2% | 73.4% | Not in our dataset |
| LiveCodeBenchCompetitive coding | Not in our dataset | Not in our dataset | Not in our dataset | 62.6% |
| ARC-AGI-2Visual reasoning | 18.9% | Not in our dataset | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | GPT-5 Mini Thinking (5.4) | 3.5 35B A3B Thinking | 3.6 35B-A3B Thinking | 3 30B A3B Thinking |
|---|---|---|---|---|
| Input | $0.25 | $0.14 | $0.1 | $0.2 |
| Output | $2 | $1 | $0.9 | $2.4 |
| Context window | 400K | 262K | 262K | 82K |
| Pricing details | Explore pricing → | Explore pricing → | Explore pricing → | Explore pricing → |
How to read this comparison
Each column keeps the exact model version you selected. Shared benchmarks are the intersection of their reported results; “all coverage” also shows where evidence is missing. Missing results never count as zero.
These are published benchmark scores, not a controlled head-to-head test. The available evidence does not establish matching evaluation settings, so we show no cross-model winner highlights or deltas. Composite quality scores are omitted because they can summarize different benchmark sets.
Scores and statistics are computed upstream. This page reads a fixed data snapshot; its date describes the snapshot, not the date of every measurement.