# Grok-2 (Dec 2024) vs Qwen3.5 35B-A3B

> Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-qwen3-5-35b-a3b
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Qwen3.5 35B-A3B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 35B-A3B leads 39.9 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 70% for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 33.7 | 42.0 |
| Rank | 239 | 123 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $2 |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 33.3 (#258)
- Qwen3.5 35B-A3B: 33.8 (#251)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1287 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |

## Reasoning

- Grok-2 (Dec 2024): 16.9 (#299)
- Qwen3.5 35B-A3B: 24.6 (#161)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1400 |
| DTBench | 65.2% | 80% |
| Epoch Capabilities Index | 130.48 | 142.52 |
| SimpleBench | 22.7% | — |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| LiveBench Reasoning | 54.8% | — |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 29.5% |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 20.8 (#284)
- Qwen3.5 35B-A3B: 39.9 (#97)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 70% |
| LMArena Math | 1283 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#233)
- Qwen3.5 35B-A3B: 47.8 (#79)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 53.8% | 83.5% |
| LMArena Expert | 1254 | 1408 |
| Confabulations | 20.1% | — |
| Vectara Hallucination Rate | — | 10.5% |

## Multilingual

- Grok-2 (Dec 2024): 43.1 (#188)
- Qwen3.5 35B-A3B: 50.0 (#127)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1282 | 1378 |
| LMArena Chinese | 1289 | 1457 |
| LMArena French | 1318 | 1412 |
| LMArena German | 1287 | 1367 |
| LMArena Japanese | 1244 | 1325 |
| LMArena Korean | 1237 | 1356 |
| LMArena Russian | 1286 | 1376 |
| LMArena Spanish | 1281 | 1392 |

## Instruction Following

- Grok-2 (Dec 2024): 66.9 (#202)
- Qwen3.5 35B-A3B: 72.8 (#128)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1379 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.8 (#190)
- Qwen3.5 35B-A3B: 42.4 (#127)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1276 | 1389 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.6 (#198)
- Qwen3.5 35B-A3B: 57.9 (#124)

| Benchmark | Grok-2 (Dec 2024) | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1305 | 1395 |
| LMArena Creative Writing | 1284 | 1346 |
| LMArena Multi-Turn | 1290 | 1390 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 33.7 on the Noometry Index.

### Is Grok-2 (Dec 2024) or Qwen3.5 35B-A3B better for coding?

They score almost the same on coding (33.3 vs 33.8); test both on your own repository before choosing.

### How many benchmarks do Grok-2 (Dec 2024) and Qwen3.5 35B-A3B share?

21 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen3.5 35B-A3B has 28.