Model comparison
GLM-4.7-Flash vs Grok-3 mini
Grok-3 mini is the stronger model overall, scoring 41.2 to 38.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GLM-4.7-Flash scores higher in 1 category and Grok-3 mini in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 35.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 77.8% for Grok-3 mini.
- GLM-4.7-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7-Flash | Grok-3 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 38.8 | 41.2 |
| Released | 2026-01-19 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.7-Flash: 40.6 (#135), Grok-3 mini: 40.8 (#131)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1383 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
Reasoning GLM-4.7-Flash leads
GLM-4.7-Flash: 20.9 (#229), Grok-3 mini: 13.6 (#334)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | — | 140.35 |
Math Grok-3 mini leads
GLM-4.7-Flash: 36.1 (#173), Grok-3 mini: 42.1 (#85)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 77.8% |
| LMArena Math | 1355 | 1386 |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
GLM-4.7-Flash: 35.5 (#184), Grok-3 mini: 46.4 (#81)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 60.5% | 76.3% |
| LMArena Expert | 1357 | 1395 |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 67.5% |
Multilingual Grok-3 mini leads
GLM-4.7-Flash: 46.5 (#158), Grok-3 mini: 48.1 (#145)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1330 | 1352 |
| LMArena Chinese | 1403 | 1387 |
| LMArena French | 1332 | 1357 |
| LMArena German | 1337 | 1349 |
| LMArena Korean | 1283 | 1335 |
| LMArena Russian | 1332 | 1353 |
| LMArena Spanish | 1350 | 1381 |
| LMArena Japanese | — | 1342 |
Instruction Following Grok-3 mini leads
GLM-4.7-Flash: 70.1 (#167), Grok-3 mini: 78.5 (#9)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1327 | 1357 |
| IFEval | — | 95.1% |
Long Context Too close to call
GLM-4.7-Flash: 40.9 (#148), Grok-3 mini: 41.0 (#147)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1345 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Grok-3 mini leads
GLM-4.7-Flash: 47.4 (#210), Grok-3 mini: 52.5 (#169)
| Benchmark | GLM-4.7-Flash | Grok-3 mini |
|---|---|---|
| LMArena Text | 1351 | 1370 |
| LMArena Creative Writing | 1297 | 1342 |
| LMArena Multi-Turn | 1342 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1125 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is GLM-4.7-Flash better than Grok-3 mini?
Grok-3 mini is the stronger model overall, scoring 41.2 to 38.8 on the Noometry Index.
Is GLM-4.7-Flash or Grok-3 mini better for coding?
They score almost the same on coding (40.6 vs 40.8); test both on your own repository before choosing.
How many benchmarks do GLM-4.7-Flash and Grok-3 mini share?
18 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Grok-3 mini has 35.