Model comparison
Grok 4.3 vs Qwen2.5-Max
Grok 4.3 is the stronger model overall, scoring 43.8 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 4.3 scores higher in 7 categories and Qwen2.5-Max in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 35.3.
Side by side
| Grok 4.3 | Qwen2.5-Max | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 43.8 | 40.7 |
| Released | 2026-04-17 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 40 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 4.3: 41.6 (#121), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1415 | 1359 |
| LMArena WebDev | 1357 | — |
| SciCode | 47.3% | — |
| WeirdML | 49.9% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 944.17 | — |
Agentic & Tool Use Not comparable
Grok 4.3: 27.7 (#99), Qwen2.5-Max: —
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| GDP.pdf | 8% | — |
| LMArena Search | 1165 | — |
| Vending-Bench 2 | 35.26 | — |
Reasoning Grok 4.3 leads
Grok 4.3: 35.9 (#68), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1360 |
| Epoch Capabilities Index | 149.16 | 132.53 |
| NYT Connections (extended) | 55.2% | — |
| CritPt | 8% | — |
| Chess Puzzles | 25% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 90.7% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 38.3% | — |
| ForecastBench | 60.3 | — |
| LiveBench | — | 62.3% |
Math Grok 4.3 leads
Grok 4.3: 46.0 (#74), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1388 | 1369 |
| FrontierMath (Tiers 1-3) | 42.8% | — |
| FrontierMath Tier 4 | 14.6% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 11% | — |
| LiveBench Math | — | 58.4% |
Knowledge Grok 4.3 leads
Grok 4.3: 52.5 (#62), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1385 | 1337 |
| GPQA Diamond | 88.8% | — |
| SimpleQA Verified | 33.2% | — |
| Confabulations | — | 21.8% |
Multimodal Not comparable
Grok 4.3: 31.6 (#104), Qwen2.5-Max: —
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1229 | — |
| Blueprint-Bench 2 | 0% | — |
Multilingual Grok 4.3 leads
Grok 4.3: 50.5 (#120), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1385 | 1352 |
| LMArena Chinese | 1422 | 1382 |
| LMArena French | 1412 | 1396 |
| LMArena German | 1395 | 1350 |
| LMArena Japanese | 1379 | 1300 |
| LMArena Korean | 1356 | 1304 |
| LMArena Russian | 1399 | 1353 |
| LMArena Spanish | 1398 | 1377 |
Instruction Following Too close to call
Grok 4.3: 72.1 (#140), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1366 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Grok 4.3 leads
Grok 4.3: 42.5 (#123), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1393 | 1358 |
Writing & Preference Grok 4.3 leads
Grok 4.3: 58.5 (#118), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Grok 4.3 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1397 | 1367 |
| LMArena Creative Writing | 1380 | 1339 |
| LMArena Multi-Turn | 1406 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench 4 | 1075 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Grok 4.3 better than Qwen2.5-Max?
Grok 4.3 is the stronger model overall, scoring 43.8 to 40.7 on the Noometry Index.
Is Grok 4.3 or Qwen2.5-Max better for coding?
They score almost the same on coding (41.6 vs 41.8); test both on your own repository before choosing.
How many benchmarks do Grok 4.3 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Qwen2.5-Max has 27.