Model comparison
Grok 4.6 vs Qwen2.5 72B Instruct
Grok 4.6 is the stronger model overall, scoring 56.9 to 31.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.6 leads 67.0 to 19.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.2% for Grok 4.6 and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 56.9 | 31.9 |
| Released | 2026-08-12 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 500K | 131K |
| Max output | 500K | 8K |
| Input $ / M tokens | $2 | $1.40 |
| Output $ / M tokens | $6 | $5.60 |
| Results tracked | 49 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 67.3% | 16% |
| LMArena Coding | 1465 | 1292 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| LMArena WebDev | 1617 | — |
| FrontierSWE | 25.3% | — |
| SciCode | 56.5% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 1,508 | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| APEX-Agents | 65.3% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| GDP.pdf | 17.2% | — |
| METR Time Horizons | — | 35.8% |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1271 |
| DTBench | 97.3% | 62.9% |
| LMCA | 48.5% | 13.4% |
| Epoch Capabilities Index | 156.44 | 129 |
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| CritPt | 19.7% | — |
| Chess Puzzles | 40% | — |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 8.1% |
| LMArena Math | 1423 | 1283 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| ProofBench | 51% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 94% | 49.1% |
| LMArena Expert | 1467 | 1245 |
| SimpleQA Verified | 49.3% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Grok 4.6: 43.6 (#23), Qwen2.5 72B Instruct: —
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1420 | 1252 |
| LMArena Chinese | 1480 | 1272 |
| LMArena French | 1461 | 1280 |
| LMArena German | 1431 | 1234 |
| LMArena Japanese | 1376 | 1180 |
| LMArena Korean | 1397 | 1188 |
| LMArena Russian | 1422 | 1264 |
| LMArena Spanish | 1404 | 1256 |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1431 | 1254 |
| IFEval | — | 80.6% |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1454 | 1282 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Grok 4.6 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1428 | 1269 |
| LMArena Creative Writing | 1428 | 1221 |
| LMArena Multi-Turn | 1425 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Grok 4.6 better than Qwen2.5 72B Instruct?
Grok 4.6 is the stronger model overall, scoring 56.9 to 31.9 on the Noometry Index.
Which is cheaper, Grok 4.6 or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Qwen2.5 72B Instruct better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 131K.
How many benchmarks do Grok 4.6 and Qwen2.5 72B Instruct share?
23 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Qwen2.5 72B Instruct has 43.