# GLM-4.6 vs Grok-3 mini

> GLM-4.6 and Grok-3 mini score almost the same on the Noometry Index (41.4 vs 41.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-grok-3-mini
- Last updated: 2026-10-11
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GLM-4.6 scores higher in 4 categories and Grok-3 mini in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6 leads 23.7 to 13.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 61.3% for Grok-3 mini.
- GLM-4.6 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.6 | Grok-3 mini |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 41.2 |
| Rank | 135 | 141 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-4.6: 40.1 (#148)
- Grok-3 mini: 40.8 (#131)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1449 | 1379 |
| SWE-bench Verified (bash only) | 55.4% | — |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 42.6% |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- Grok-3 mini: —

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.7 (#172)
- Grok-3 mini: 13.6 (#334)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 61.3% |
| LMArena Hard Prompts | 1440 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| ARC-AGI-1 | — | 16.5% |
| CritPt | 1.1% | — |
| Epoch Capabilities Index | — | 140.35 |

## Math

- GLM-4.6: 39.1 (#111)
- Grok-3 mini: 42.1 (#85)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Math | 1432 | 1386 |
| FrontierMath (Feb 2025 set) | 3.8% | 5.9% |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 40.2 (#124)
- Grok-3 mini: 46.4 (#81)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1431 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 9.5% | — |
| GPQA (HELM) | — | 67.5% |

## Multilingual

- GLM-4.6: 53.5 (#66)
- Grok-3 mini: 48.1 (#145)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1426 | 1352 |
| LMArena Chinese | 1499 | 1387 |
| LMArena French | 1459 | 1357 |
| LMArena German | 1447 | 1349 |
| LMArena Japanese | 1393 | 1342 |
| LMArena Korean | 1400 | 1335 |
| LMArena Russian | 1419 | 1353 |
| LMArena Spanish | 1436 | 1381 |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- Grok-3 mini: 78.5 (#9)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1410 | 1357 |
| IFEval | — | 95.1% |

## Long Context

- GLM-4.6: 43.4 (#94)
- Grok-3 mini: 41.0 (#147)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1422 | 1372 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- Grok-3 mini: 52.5 (#169)

| Benchmark | GLM-4.6 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1440 | 1370 |
| LMArena Creative Writing | 1411 | 1342 |
| LMArena Multi-Turn | 1427 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1411 | — |
| WildBench | — | 65.1% |

## FAQ

### Is GLM-4.6 better than Grok-3 mini?

GLM-4.6 and Grok-3 mini score almost the same on the Noometry Index (41.4 vs 41.2), so choose on price, context window or the category you care about most.

### Is GLM-4.6 or Grok-3 mini better for coding?

They score almost the same on coding (40.1 vs 40.8); test both on your own repository before choosing.

### How many benchmarks do GLM-4.6 and Grok-3 mini share?

19 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Grok-3 mini has 35.