Model comparison
Grok 4.20 (Non-Reasoning) vs Qwen2.5-Max
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 40.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Qwen2.5-Max in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 25.6.
Side by side
| Grok 4.20 (Non-Reasoning) | Qwen2.5-Max | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 48.6 | 40.7 |
| Released | 2026-02-17 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 46 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1459 | 1359 |
| LMArena WebDev | 1375 | — |
| WeirdML | 52.3% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen2.5-Max: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1360 |
| Epoch Capabilities Index | 151.98 | 132.53 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 38.7% | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 62.3% |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1455 | 1369 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
| LiveBench Math | — | 58.4% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1439 | 1337 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| Confabulations | — | 21.8% |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen2.5-Max: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1441 | 1352 |
| LMArena Chinese | 1481 | 1382 |
| LMArena French | 1476 | 1396 |
| LMArena German | 1465 | 1350 |
| LMArena Japanese | 1449 | 1300 |
| LMArena Korean | 1417 | 1304 |
| LMArena Russian | 1458 | 1353 |
| LMArena Spanish | 1443 | 1377 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1420 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1437 | 1358 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1451 | 1367 |
| LMArena Creative Writing | 1438 | 1339 |
| LMArena Multi-Turn | 1456 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1574 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Qwen2.5-Max?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 40.7 on the Noometry Index.
Is Grok 4.20 (Non-Reasoning) or Qwen2.5-Max better for coding?
They score almost the same on coding (42.1 vs 41.8); test both on your own repository before choosing.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen2.5-Max share?
18 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen2.5-Max has 27.