Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
3 benchmarks in common.
4 models selected. 3 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | OpenAI | DeepSeek | Qwen | Qwen |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,415 | 1,358 | 1,347 | Not in our dataset |
| LiveBench 1.0General reasoning | 69.8% | 60.5% | 59.8% | 59.6% |
| GPQA DiamondScientific knowledge | 66.3% | 59.1% | 54.6% | 54.8% |
| HLEAcademic reasoning | 5.4% | Not in our dataset | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | 81.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| SimpleBenchCommonsense reasoning | 27.0% | 18.9% | Not in our dataset | Not in our dataset |
| AIME 2025Mathematics | 37.0% | 28.8% | 20.2% | 23.3% |
| AiderCode editing | 52.4% | 49.6% | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | 54.6% | Not in our dataset | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | Not in our dataset | 36.2% | 31.3% | 29.0% |
| Tau-BenchAgentic tool use | 68.0% | Not in our dataset | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | 0.4% | Not in our dataset | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | GPT-4.1 Non-thinking | v3 (Non-thinking) | 3 32B Non-thinking | 3 14B Non-thinking |
|---|---|---|---|---|
| Input | $3 | $0.257 | $0.08 | $0.12 |
| Output | $12 | $1.029 | $0.28 | $0.24 |
| Context window | Not available | 164K | 131K | 41K |
| 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.