Model comparison
GLM-4.6V vs Grok-3 mini
GLM-4.6V and Grok-3 mini score almost the same on the Noometry Index (41.3 vs 41.2), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GLM-4.6V scores higher in 5 categories and Grok-3 mini in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6V leads 27.6 to 13.6.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6V | Grok-3 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.3 | 41.2 |
| Released | 2025-12-08 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 12 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.6V: 40.9 (#128), Grok-3 mini: 40.8 (#131)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1390 | 1379 |
| Aider Polyglot | — | 49.3% |
| WeirdML | — | 42.6% |
Reasoning GLM-4.6V leads
GLM-4.6V: 27.6 (#115), Grok-3 mini: 13.6 (#334)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |
Math Not comparable
GLM-4.6V: —, Grok-3 mini: 42.1 (#85)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| LMArena Math | — | 1386 |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
GLM-4.6V: 38.0 (#149), Grok-3 mini: 46.4 (#81)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1371 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
GLM-4.6V: 34.8 (#90), Grok-3 mini: —
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1164 | — |
Multilingual Too close to call
GLM-4.6V: 48.6 (#141), Grok-3 mini: 48.1 (#145)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1359 | 1352 |
| LMArena Chinese | 1425 | 1387 |
| LMArena Russian | 1340 | 1353 |
| LMArena French | — | 1357 |
| LMArena German | — | 1349 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1335 |
| LMArena Spanish | — | 1381 |
Instruction Following Grok-3 mini leads
GLM-4.6V: 71.4 (#151), Grok-3 mini: 78.5 (#9)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1352 | 1357 |
| IFEval | — | 95.1% |
Long Context Too close to call
GLM-4.6V: 41.3 (#143), Grok-3 mini: 41.0 (#147)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1358 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GLM-4.6V leads
GLM-4.6V: 56.6 (#137), Grok-3 mini: 52.5 (#169)
| Benchmark | GLM-4.6V | Grok-3 mini |
|---|---|---|
| LMArena Text | 1377 | 1370 |
| LMArena Creative Writing | 1347 | 1342 |
| LMArena Multi-Turn | 1360 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
Frequently asked questions
Is GLM-4.6V better than Grok-3 mini?
GLM-4.6V and Grok-3 mini score almost the same on the Noometry Index (41.3 vs 41.2), so choose on price, context window or the category you care about most.
Is GLM-4.6V or Grok-3 mini better for coding?
They score almost the same on coding (40.9 vs 40.8); test both on your own repository before choosing.
How many benchmarks do GLM-4.6V and Grok-3 mini share?
11 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Grok-3 mini has 35.