# GLM-4.7 vs Grok-3 mini

> GLM-4.7 and Grok-3 mini score almost the same on the Noometry Index (42.0 vs 41.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-grok-3-mini
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-4.7 scores higher in 6 categories and Grok-3 mini in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.7 leads 24.3 to 13.6.
- The biggest single-benchmark swing is GPQA Diamond: 83.3% for GLM-4.7 and 76.3% for Grok-3 mini.
- GLM-4.7 has downloadable open weights; the other is API-only.

## Snapshot

| | GLM-4.7 | Grok-3 mini |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 42.0 | 41.2 |
| Rank | 124 | 141 |
| Context | 205K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.20 | — |
| Weights | Open | Proprietary |

## Coding

- GLM-4.7: 44.0 (#79)
- Grok-3 mini: 40.8 (#131)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1454 | 1379 |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 42.6% |
| ALE-Bench | 399.48 | — |

## Agentic & Tool Use

- GLM-4.7: 26.5 (#103)
- Grok-3 mini: —

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 24.3 (#164)
- Grok-3 mini: 13.6 (#334)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1375 |
| Epoch Capabilities Index | 143.51 | 140.35 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |

## Math

- GLM-4.7: 38.6 (#135)
- Grok-3 mini: 42.1 (#85)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 77.8% |
| LMArena Math | 1423 | 1386 |
| FrontierMath (Feb 2025 set) | 2.4% | 5.9% |
| ProofBench | 6% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#80)
- Grok-3 mini: 46.4 (#81)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 83.3% | 76.3% |
| LMArena Expert | 1424 | 1395 |
| SimpleQA Verified | 32.2% | — |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 11.7% | — |
| GPQA (HELM) | — | 67.5% |

## Multilingual

- GLM-4.7: 52.8 (#79)
- Grok-3 mini: 48.1 (#145)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1417 | 1352 |
| LMArena Chinese | 1495 | 1387 |
| LMArena French | 1432 | 1357 |
| LMArena German | 1424 | 1349 |
| LMArena Japanese | 1439 | 1342 |
| LMArena Korean | 1399 | 1335 |
| LMArena Russian | 1423 | 1353 |
| LMArena Spanish | 1434 | 1381 |

## Instruction Following

- GLM-4.7: 74.4 (#95)
- Grok-3 mini: 78.5 (#9)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1411 | 1357 |
| IFEval | — | 95.1% |

## Long Context

- GLM-4.7: 42.8 (#116)
- Grok-3 mini: 41.0 (#147)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1432 | 1372 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 60.9 (#93)
- Grok-3 mini: 52.5 (#169)

| Benchmark | GLM-4.7 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1435 | 1370 |
| LMArena Creative Writing | 1401 | 1342 |
| LMArena Multi-Turn | 1446 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1413 | — |
| WildBench | — | 65.1% |

## FAQ

### Is GLM-4.7 better than Grok-3 mini?

GLM-4.7 and Grok-3 mini score almost the same on the Noometry Index (42.0 vs 41.2), so choose on price, context window or the category you care about most.

### Is GLM-4.7 or Grok-3 mini better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 40.8 in the Noometry coding category.

### How many benchmarks do GLM-4.7 and Grok-3 mini share?

21 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Grok-3 mini has 35.