Model comparison
GLM-5V-Turbo vs Grok-3 mini
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. GLM-5V-Turbo scores higher in 5 categories and Grok-3 mini in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5V-Turbo leads 29.7 to 13.6.
Side by side
| GLM-5V-Turbo | Grok-3 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 43.8 | 41.2 |
| Released | 2026-04-01 | 2025-04-09 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.20 | — |
| Output $ / M tokens | $4 | — |
| Results tracked | 19 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5V-Turbo leads
GLM-5V-Turbo: 42.1 (#111), Grok-3 mini: 40.8 (#131)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Coding | 1466 | 1379 |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1401 | — |
| WeirdML | — | 42.6% |
Reasoning GLM-5V-Turbo leads
GLM-5V-Turbo: 29.7 (#89), Grok-3 mini: 13.6 (#334)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1375 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 16.5% |
| Epoch Capabilities Index | — | 140.35 |
Math Grok-3 mini leads
GLM-5V-Turbo: 39.4 (#106), Grok-3 mini: 42.1 (#85)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Math | 1441 | 1386 |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
Knowledge Grok-3 mini leads
GLM-5V-Turbo: 40.6 (#117), Grok-3 mini: 46.4 (#81)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Expert | 1452 | 1395 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| GPQA (HELM) | — | 67.5% |
Multimodal Not comparable
GLM-5V-Turbo: 40.9 (#42), Grok-3 mini: —
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Vision | 1264 | — |
| LMArena Document | 1416 | — |
Multilingual GLM-5V-Turbo leads
GLM-5V-Turbo: 53.0 (#73), Grok-3 mini: 48.1 (#145)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1420 | 1352 |
| LMArena Chinese | 1488 | 1387 |
| LMArena French | 1444 | 1357 |
| LMArena German | 1423 | 1349 |
| LMArena Korean | 1396 | 1335 |
| LMArena Russian | 1431 | 1353 |
| LMArena Spanish | 1450 | 1381 |
| LMArena Japanese | — | 1342 |
Instruction Following Grok-3 mini leads
GLM-5V-Turbo: 75.0 (#80), Grok-3 mini: 78.5 (#9)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1423 | 1357 |
| IFEval | — | 95.1% |
Long Context GLM-5V-Turbo leads
GLM-5V-Turbo: 44.0 (#80), Grok-3 mini: 41.0 (#147)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1438 | 1372 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GLM-5V-Turbo leads
GLM-5V-Turbo: 62.5 (#73), Grok-3 mini: 52.5 (#169)
| Benchmark | GLM-5V-Turbo | Grok-3 mini |
|---|---|---|
| LMArena Text | 1437 | 1370 |
| LMArena Creative Writing | 1416 | 1342 |
| LMArena Multi-Turn | 1432 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| WildBench | — | 65.1% |
Frequently asked questions
Is GLM-5V-Turbo better than Grok-3 mini?
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index.
Is GLM-5V-Turbo or Grok-3 mini better for coding?
GLM-5V-Turbo scores higher on coding benchmarks: 42.1 versus 40.8 in the Noometry coding category.
How many benchmarks do GLM-5V-Turbo and Grok-3 mini share?
16 benchmarks have published results for both models. GLM-5V-Turbo has 19 scored results on Noometry and Grok-3 mini has 35.