Model comparison
GLM-4.5 vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 42.0 on the Noometry Index. GLM-4.5 costs 1.6× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GLM-4.5 scores higher in 2 categories and Grok 4.3 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 35.9.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 49.9% for Grok 4.3.
- GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Grok 4.3 accepts more context: 1M tokens versus 131K.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | Grok 4.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 42.0 | 43.8 |
| Released | 2025-07-27 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 98K | 30K |
| Input $ / M tokens | $0.60 | $1.25 |
| Output $ / M tokens | $2.20 | $2.50 |
| Results tracked | 27 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5: 41.4 (#125), Grok 4.3: 41.6 (#121)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| WeirdML | 40.6% | 49.9% |
| LMArena Coding | 1434 | 1415 |
| ALE-Bench | 344.82 | 944.17 |
| SWE-bench Verified (bash only) | 54.2% | — |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, Grok 4.3: 27.7 (#99)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
GLM-4.5: 28.6 (#100), Grok 4.3: 35.9 (#68)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1396 |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | — | 55.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
| Epoch Capabilities Index | — | 149.16 |
| ForecastBench | — | 60.3 |
Math Grok 4.3 leads
GLM-4.5: 39.0 (#116), Grok 4.3: 46.0 (#74)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Math | 1427 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |
Knowledge Grok 4.3 leads
GLM-4.5: 35.9 (#179), Grok 4.3: 52.5 (#62)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Expert | 1433 | 1385 |
| GPQA Diamond | — | 88.8% |
| Humanity's Last Exam | 8.3% | — |
| SimpleQA Verified | — | 33.2% |
| Confabulations | 11.3% | — |
Multimodal Not comparable
GLM-4.5: —, Grok 4.3: 31.6 (#104)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual GLM-4.5 leads
GLM-4.5: 52.8 (#77), Grok 4.3: 50.5 (#120)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1417 | 1385 |
| LMArena Chinese | 1465 | 1422 |
| LMArena French | 1418 | 1412 |
| LMArena German | 1407 | 1395 |
| LMArena Japanese | 1415 | 1379 |
| LMArena Korean | 1380 | 1356 |
| LMArena Russian | 1414 | 1399 |
| LMArena Spanish | 1454 | 1398 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.1 (#104), Grok 4.3: 72.1 (#140)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1366 |
Long Context Grok 4.3 leads
GLM-4.5: 38.2 (#201), Grok 4.3: 42.5 (#123)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1412 | 1393 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Too close to call
GLM-4.5: 57.5 (#127), Grok 4.3: 58.5 (#118)
| Benchmark | GLM-4.5 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1430 | 1397 |
| LMArena Creative Writing | 1395 | 1380 |
| LMArena Multi-Turn | 1415 | 1406 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GLM-4.5 better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 42.0 on the Noometry Index. GLM-4.5 costs 1.6× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5 or Grok 4.3?
GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is GLM-4.5 or Grok 4.3 better for coding?
They score almost the same on coding (41.4 vs 41.6); test both on your own repository before choosing.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 131K.
How many benchmarks do GLM-4.5 and Grok 4.3 share?
19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Grok 4.3 has 40.