Model comparison
Grok 3 vs Qwen2.5-Max
Grok 3 and Qwen2.5-Max score almost the same on the Noometry Index (39.6 vs 40.1), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Grok 3 scores higher in 6 categories and Qwen2.5-Max in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 3 leads 46.0 to 34.8.
- The biggest single-benchmark swing is Confabulations: 14.2% for Grok 3 and 21.8% for Qwen2.5-Max.
Side by side
| Grok 3 | Qwen2.5-Max | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 40.1 |
| Released | 2025-04-09 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 40 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 3: 41.5 (#113), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1432 | 1359 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
| LiveBench Coding | — | 64.4% |
Agentic & Tool Use Not comparable
Grok 3: 30.2 (#69), Qwen2.5-Max: —
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Qwen2.5-Max leads
Grok 3: 13.8 (#322), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1360 |
| Epoch Capabilities Index | 138.34 | 132.54 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |
Math Grok 3 leads
Grok 3: 36.2 (#122), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1390 | 1369 |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| Confabulations | 14.2% | 21.8% |
| LMArena Expert | 1420 | 1337 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1411 | 1352 |
| LMArena Chinese | 1448 | 1382 |
| LMArena French | 1460 | 1396 |
| LMArena German | 1431 | 1350 |
| LMArena Japanese | 1389 | 1299 |
| LMArena Korean | 1374 | 1304 |
| LMArena Russian | 1416 | 1353 |
| LMArena Spanish | 1417 | 1377 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1409 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 88.4% | — |
Long Context Qwen2.5-Max leads
Grok 3: 38.7 (#187), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1439 | 1358 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Too close to call
Grok 3: 56.0 (#136), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Grok 3 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1426 | 1367 |
| LMArena Creative Writing | 1414 | 1339 |
| Short-Story Creative Writing | 76.4% | 72.9% |
| LMArena Multi-Turn | 1424 | 1364 |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Grok 3 better than Qwen2.5-Max?
Grok 3 and Qwen2.5-Max score almost the same on the Noometry Index (39.6 vs 40.1), so choose on price, context window or the category you care about most.
Is Grok 3 or Qwen2.5-Max better for coding?
They score almost the same on coding (41.5 vs 41.2); test both on your own repository before choosing.
How many benchmarks do Grok 3 and Qwen2.5-Max share?
20 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Qwen2.5-Max has 27.