Model comparison
Grok 4.5 vs Qwen2.5-Coder-32B
Grok 4.5 is the stronger model overall, scoring 55.0 to 32.9 on the Noometry Index. Qwen2.5-Coder-32B costs 4.0× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Grok 4.5 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.5 leads 56.0 to 20.4.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $6 for Grok 4.5.
- Grok 4.5 accepts more context: 500K tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.5 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 55.0 | 32.9 |
| Released | 2026-07-08 | 2024-09-18 |
| Weights | Proprietary | Open |
| Context window | 500K | 33K |
| Max output | 500K | 29K |
| Input $ / M tokens | $2 | $0.66 |
| Output $ / M tokens | $6 | $1 |
| Results tracked | 52 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.5 leads
Grok 4.5: 51.7 (#34), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1473 | 1276 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.4% | — |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1552 | — |
| SciCode | 54.1% | — |
| WeirdML | 46.4% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 1,309 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
Grok 4.5: 44.4 (#15), Qwen2.5-Coder-32B: —
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| APEX-Agents | 56.2% | — |
| τ²-bench Banking | 47.9% | — |
| PostTrainBench | 23.4% | — |
| GBAEval | 65.4% | — |
| GDP.pdf | 14% | — |
| LMArena Search | 1213 | — |
| Vending-Bench 2 | 3,887 | — |
Reasoning Grok 4.5 leads
Grok 4.5: 56.0 (#23), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1462 | 1251 |
| Epoch Capabilities Index | 154.02 | 119.41 |
| ARC-AGI-2 | 52.6% | — |
| SimpleBench | 70% | — |
| Kagi LLM Benchmark | 83.5% | — |
| NYT Connections (extended) | 79.9% | — |
| ARC-AGI-1 | 87.2% | — |
| CritPt | 15.4% | — |
| Chess Puzzles | 36% | — |
| LiveBench Reasoning | — | 42.1% |
| DTBench | 96.5% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 45.2% | — |
| Surface Evolver Bench | 74.4% | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Grok 4.5 leads
Grok 4.5: 60.7 (#29), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1457 | 1251 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 24.4% | — |
| OTIS Mock AIME 2024-2025 | 97.8% | — |
| ProofBench | 31% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Grok 4.5 leads
Grok 4.5: 62.3 (#21), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1466 | 1221 |
| GPQA Diamond | 93.4% | — |
| SimpleQA Verified | 48.3% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
Grok 4.5: 37.8 (#63), Qwen2.5-Coder-32B: —
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1287 | — |
| Blueprint-Bench 2 | 27.3% | — |
| Furniture Assembly | 22.5% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.5 leads
Grok 4.5: 54.5 (#43), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1439 | 1205 |
| LMArena Chinese | 1497 | 1222 |
| LMArena Russian | 1447 | 1228 |
| LMArena French | 1458 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1425 | — |
| LMArena Korean | 1402 | — |
| LMArena Spanish | 1452 | — |
Instruction Following Grok 4.5 leads
Grok 4.5: 76.3 (#45), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1446 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Grok 4.5 leads
Grok 4.5: 44.8 (#54), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1463 | 1251 |
Writing & Preference Grok 4.5 leads
Grok 4.5: 65.9 (#40), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | Grok 4.5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1448 | 1230 |
| LMArena Creative Writing | 1442 | 1174 |
| LMArena Multi-Turn | 1457 | 1222 |
| EQ-Bench Creative Writing | 1579 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Grok 4.5 better than Qwen2.5-Coder-32B?
Grok 4.5 is the stronger model overall, scoring 55.0 to 32.9 on the Noometry Index. Qwen2.5-Coder-32B costs 4.0× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.
Which is cheaper, Grok 4.5 or Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Grok 4.5 lists at $2 and $6.
Is Grok 4.5 or Qwen2.5-Coder-32B better for coding?
Grok 4.5 scores higher on coding benchmarks: 51.7 versus 22.4 in the Noometry coding category.
Which has the bigger context window?
Grok 4.5 does, with 500K tokens against 33K.
How many benchmarks do Grok 4.5 and Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and Qwen2.5-Coder-32B has 31.