Model comparison
Grok-3 mini vs Qwen3.5-9B
Grok-3 mini is the stronger model overall, scoring 41.0 to 33.3 on the Noometry Index.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Grok-3 mini scores higher in 3 categories and Qwen3.5-9B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-9B leads 22.5 to 13.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 61.7% for Qwen3.5-9B.
- Qwen3.5-9B has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Qwen3.5-9B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 41.0 | 33.3 |
| Released | 2025-04-09 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 35 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.4 (#126), Qwen3.5-9B: 35.3 (#213)
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| Aider Polyglot | 49.3% | — |
| SciCode | — | 27.5% |
| WeirdML | 42.6% | — |
| LMArena Coding | 1380 | — |
Agentic & Tool Use Not comparable
Grok-3 mini: —, Qwen3.5-9B: 14.4 (#143)
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
Reasoning Qwen3.5-9B leads
Grok-3 mini: 13.8 (#323), Qwen3.5-9B: 22.5 (#178)
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| Epoch Capabilities Index | 140.35 | 139.45 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | 1374 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
Math Grok-3 mini leads
Grok-3 mini: 40.3 (#78), Qwen3.5-9B: 33.5 (#174)
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| Omni-MATH | 31.8% | — |
| LMArena Math | 1386 | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Too close to call
Grok-3 mini: 46.3 (#75), Qwen3.5-9B: 46.0 (#77)
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 76.3% | 79% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
Multilingual Not comparable
Grok-3 mini: 48.3 (#141), Qwen3.5-9B: —
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1352 | — |
| LMArena Chinese | 1387 | — |
| LMArena French | 1357 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1343 | — |
| LMArena Korean | 1336 | — |
| LMArena Russian | 1352 | — |
| LMArena Spanish | 1379 | — |
Instruction Following Not comparable
Grok-3 mini: 78.7 (#8), Qwen3.5-9B: —
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| IFEval | 95.1% | — |
| LMArena Instruction Following | 1356 | — |
Long Context Not comparable
Grok-3 mini: 41.0 (#142), Qwen3.5-9B: —
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference Not comparable
Grok-3 mini: 52.7 (#163), Qwen3.5-9B: —
| Benchmark | Grok-3 mini | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1370 | — |
| LMArena Creative Writing | 1342 | — |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
| LMArena Multi-Turn | 1355 | — |
Frequently asked questions
Is Grok-3 mini better than Qwen3.5-9B?
Grok-3 mini is the stronger model overall, scoring 41.0 to 33.3 on the Noometry Index.
Is Grok-3 mini or Qwen3.5-9B better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.4 versus 35.3 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Qwen3.5-9B share?
3 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen3.5-9B has 10.