Model comparison
GLM-5 vs Grok-3 mini
GLM-5 is the stronger model overall, scoring 45.9 to 41.0 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. GLM-5 scores higher in 7 categories and Grok-3 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5 leads 27.6 to 13.8.
- The biggest single-benchmark swing is ARC-AGI-1: 44.7% for GLM-5 and 16.5% for Grok-3 mini.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | Grok-3 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 45.9 | 41.0 |
| Released | 2026-02-11 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 45 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#47), Grok-3 mini: 40.4 (#126)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| WeirdML | 48.2% | 42.6% |
| LMArena Coding | 1461 | 1380 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| Aider Polyglot | — | 49.3% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use Not comparable
GLM-5: 30.9 (#65), Grok-3 mini: —
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#100), Grok-3 mini: 13.8 (#323)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| ARC-AGI-2 | 4.9% | 0.4% |
| Kagi LLM Benchmark | 75% | 61.3% |
| ARC-AGI-1 | 44.7% | 16.5% |
| LMArena Hard Prompts | 1451 | 1374 |
| Epoch Capabilities Index | 145.84 | 140.35 |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | 74.8% | — |
| Chess Puzzles | 10% | — |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 44.8 (#66), Grok-3 mini: 40.3 (#78)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 77.8% |
| LMArena Math | 1440 | 1386 |
| FrontierMath (Feb 2025 set) | 16.4% | 5.9% |
| MathArena Final-Answer Competitions | 65.7% | — |
| Omni-MATH | — | 31.8% |
| MATH Level 5 | — | 90.9% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5 leads
GLM-5: 52.2 (#59), Grok-3 mini: 46.3 (#75)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| GPQA Diamond | 87.8% | 76.3% |
| LMArena Expert | 1454 | 1395 |
| MMLU-Pro | — | 79.9% |
| Confabulations | — | 10.8% |
| Vectara Hallucination Rate | 10.1% | — |
| GPQA (HELM) | — | 67.5% |
Multilingual GLM-5 leads
GLM-5: 53.9 (#57), Grok-3 mini: 48.3 (#141)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| LMArena Non-English | 1430 | 1352 |
| LMArena Chinese | 1511 | 1387 |
| LMArena French | 1455 | 1357 |
| LMArena German | 1445 | 1350 |
| LMArena Japanese | 1416 | 1343 |
| LMArena Korean | 1421 | 1336 |
| LMArena Russian | 1436 | 1352 |
| LMArena Spanish | 1452 | 1379 |
Instruction Following Grok-3 mini leads
GLM-5: 75.4 (#64), Grok-3 mini: 78.7 (#8)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| LMArena Instruction Following | 1427 | 1356 |
| IFEval | — | 95.1% |
Long Context GLM-5 leads
GLM-5: 44.6 (#58), Grok-3 mini: 41.0 (#142)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| LMArena Longer Query | 1446 | 1372 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.2 (#38), Grok-3 mini: 52.7 (#163)
| Benchmark | GLM-5 | Grok-3 mini |
|---|---|---|
| LMArena Text | 1446 | 1370 |
| LMArena Creative Writing | 1438 | 1342 |
| LMArena Multi-Turn | 1456 | 1355 |
| Short-Story Creative Writing | — | 73.5% |
| EQ-Bench Creative Writing | 1601 | — |
| WildBench | — | 65.1% |
Frequently asked questions
Is GLM-5 better than Grok-3 mini?
GLM-5 is the stronger model overall, scoring 45.9 to 41.0 on the Noometry Index.
Is GLM-5 or Grok-3 mini better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 40.4 in the Noometry coding category.
How many benchmarks do GLM-5 and Grok-3 mini share?
25 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Grok-3 mini has 35.