Model comparison
GLM-5.1 vs Grok 4.3
GLM-5.1 is the stronger model overall, scoring 47.6 to 43.6 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Grok 4.3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.1 leads 67.2 to 58.6.
- The biggest single-benchmark swing is NYT Connections (extended): 77.7% for GLM-5.1 and 55.2% for Grok 4.3.
- Grok 4.3 is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Grok 4.3 accepts more context: 1M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | Grok 4.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 47.6 | 43.6 |
| Released | 2026-04-07 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 200K | 1M |
| Max output | 131K | 30K |
| Input $ / M tokens | $1.40 | $1.25 |
| Output $ / M tokens | $4.40 | $2.50 |
| Results tracked | 41 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.5 (#52), Grok 4.3: 41.3 (#117)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1509 | 1357 |
| SciCode | 43.8% | 47.3% |
| WeirdML | 57.1% | 49.9% |
| LMArena Coding | 1486 | 1415 |
| ALE-Bench | 887.1 | 944.17 |
| SWE-bench Verified | 74.2% | — |
Agentic & Tool Use Grok 4.3 leads
GLM-5.1: 24.8 (#106), Grok 4.3: 27.6 (#93)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| Vending-Bench 2 | 5,634 | 35.26 |
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
Reasoning GLM-5.1 leads
GLM-5.1: 38.2 (#57), Grok 4.3: 34.9 (#60)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 77.7% | 55.2% |
| CritPt | 4.6% | 8% |
| Chess Puzzles | 19% | 25% |
| LMArena Hard Prompts | 1472 | 1397 |
| Epoch Capabilities Index | 149.86 | 149.13 |
| SimpleBench | 55.1% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
| ForecastBench | — | 60.3 |
Math GLM-5.1 leads
GLM-5.1: 49.0 (#48), Grok 4.3: 45.8 (#60)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 42.8% |
| OTIS Mock AIME 2024-2025 | 93.3% | 93.3% |
| ProofBench | 22.2% | 11% |
| LMArena Math | 1472 | 1388 |
| FrontierMath Tier 4 | — | 14.6% |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 55.0 (#45), Grok 4.3: 52.5 (#57)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 89.9% | 88.8% |
| SimpleQA Verified | 34% | 33.2% |
| LMArena Expert | 1477 | 1385 |
Multimodal Not comparable
GLM-5.1: —, Grok 4.3: 31.6 (#96)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1231 |
| Blueprint-Bench 2 | — | 0% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.2 (#34), Grok 4.3: 50.7 (#114)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1448 | 1385 |
| LMArena Chinese | 1516 | 1423 |
| LMArena French | 1478 | 1412 |
| LMArena German | 1466 | 1395 |
| LMArena Japanese | 1436 | 1379 |
| LMArena Korean | 1423 | 1357 |
| LMArena Russian | 1453 | 1399 |
| LMArena Spanish | 1467 | 1402 |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.5 (#41), Grok 4.3: 72.3 (#135)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1366 |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#51), Grok 4.3: 42.5 (#118)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1467 | 1393 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 67.2 (#29), Grok 4.3: 58.6 (#112)
| Benchmark | GLM-5.1 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1462 | 1397 |
| LMArena Creative Writing | 1454 | 1380 |
| LMArena Multi-Turn | 1473 | 1406 |
| EQ-Bench Creative Writing | 1592 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GLM-5.1 better than Grok 4.3?
GLM-5.1 is the stronger model overall, scoring 47.6 to 43.6 on the Noometry Index.
Which is cheaper, GLM-5.1 or Grok 4.3?
Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Grok 4.3 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.5 versus 41.3 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 200K.
How many benchmarks do GLM-5.1 and Grok 4.3 share?
31 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Grok 4.3 has 40.