Model comparison
Grok-2 (Dec 2024) vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 397B-A17B leads 46.1 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 88.9% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 33.7 | 46.0 |
| Released | 2024-08-13 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 34 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 33.3 (#258), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1287 | 1465 |
| LMArena WebDev | — | 1400 |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |
Agentic & Tool Use Not comparable
Grok-2 (Dec 2024): —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 16.9 (#299), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1448 |
| DTBench | 65.2% | 87.5% |
| Epoch Capabilities Index | 130.48 | 146.65 |
| SimpleBench | 22.7% | — |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 54.8% | — |
| Mystery Game Puzzles | — | 18% |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 37.9% |
| LiveBench | 54.3% | — |
Math Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 20.8 (#284), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 88.9% |
| LMArena Math | 1283 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 29.8 (#233), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 53.8% | 86.4% |
| LMArena Expert | 1254 | 1462 |
| Confabulations | 20.1% | — |
Multimodal Not comparable
Grok-2 (Dec 2024): —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 43.1 (#188), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1282 | 1430 |
| LMArena Chinese | 1289 | 1500 |
| LMArena French | 1318 | 1461 |
| LMArena German | 1287 | 1447 |
| LMArena Japanese | 1244 | 1426 |
| LMArena Korean | 1237 | 1384 |
| LMArena Russian | 1286 | 1429 |
| LMArena Spanish | 1281 | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 66.9 (#202), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1424 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 38.8 (#190), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1276 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Grok-2 (Dec 2024): 48.6 (#198), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1305 | 1438 |
| LMArena Creative Writing | 1284 | 1401 |
| LMArena Multi-Turn | 1290 | 1446 |
| Short-Story Creative Writing | 63.6% | — |
| EQ-Bench Creative Writing | — | 1478 |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 33.3 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Qwen3.5 397B-A17B share?
21 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen3.5 397B-A17B has 36.