Model comparison
GLM-5 vs Grok 4.3
GLM-5 is the stronger model overall, scoring 46.1 to 43.8 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GLM-5 scores higher in 7 categories and Grok 4.3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 27.6.
- The biggest single-benchmark swing is NYT Connections (extended): 74.8% for GLM-5 and 55.2% for Grok 4.3.
- Both cost about the same: $1 input and $3.20 output per million tokens.
- Grok 4.3 accepts more context: 1M tokens versus 205K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | Grok 4.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 46.1 | 43.8 |
| Released | 2026-02-11 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 30K |
| Input $ / M tokens | $1 | $1.25 |
| Output $ / M tokens | $3.20 | $2.50 |
| Results tracked | 45 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Grok 4.3: 41.6 (#121)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1434 | 1357 |
| WeirdML | 48.2% | 49.9% |
| LMArena Coding | 1461 | 1415 |
| ALE-Bench | 765.62 | 944.17 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 47.3% |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Grok 4.3: 27.7 (#99)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| Vending-Bench 2 | 4,432 | 35.26 |
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
Reasoning Grok 4.3 leads
GLM-5: 27.6 (#116), Grok 4.3: 35.9 (#68)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 74.8% | 55.2% |
| Chess Puzzles | 10% | 25% |
| LMArena Hard Prompts | 1452 | 1396 |
| Epoch Capabilities Index | 145.83 | 149.16 |
| ForecastBench | 61 | 60.3 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 8% |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
Math Too close to call
GLM-5: 46.4 (#71), Grok 4.3: 46.0 (#74)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 93.3% |
| LMArena Math | 1440 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| MathArena Final-Answer Competitions | 65.7% | — |
| ProofBench | — | 11% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GLM-5: 52.3 (#64), Grok 4.3: 52.5 (#62)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 87.8% | 88.8% |
| LMArena Expert | 1454 | 1385 |
| SimpleQA Verified | — | 33.2% |
| Vectara Hallucination Rate | 10.1% | — |
Multimodal Not comparable
GLM-5: —, Grok 4.3: 31.6 (#104)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), Grok 4.3: 50.5 (#120)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1430 | 1385 |
| LMArena Chinese | 1511 | 1422 |
| LMArena French | 1455 | 1412 |
| LMArena German | 1445 | 1395 |
| LMArena Japanese | 1416 | 1379 |
| LMArena Korean | 1423 | 1356 |
| LMArena Russian | 1436 | 1399 |
| LMArena Spanish | 1454 | 1398 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), Grok 4.3: 72.1 (#140)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1366 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), Grok 4.3: 42.5 (#123)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1446 | 1393 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), Grok 4.3: 58.5 (#118)
| Benchmark | GLM-5 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1446 | 1397 |
| LMArena Creative Writing | 1439 | 1380 |
| LMArena Multi-Turn | 1456 | 1406 |
| EQ-Bench Creative Writing | 1601 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GLM-5 better than Grok 4.3?
GLM-5 is the stronger model overall, scoring 46.1 to 43.8 on the Noometry Index.
Which is cheaper, GLM-5 or Grok 4.3?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is GLM-5 or Grok 4.3 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 41.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 205K.
How many benchmarks do GLM-5 and Grok 4.3 share?
27 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Grok 4.3 has 40.