Model comparison
GLM-4.7 vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 42.0 on the Noometry Index. GLM-4.7 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 . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GLM-4.7 scores higher in 5 categories and Grok 4.3 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.3 leads 35.9 to 24.3.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 25% for Grok 4.3.
- GLM-4.7 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 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | Grok 4.3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 42.0 | 43.8 |
| Released | 2025-12-22 | 2026-04-17 |
| Weights | Open | Proprietary |
| Context window | 205K | 1M |
| Max output | 131K | 30K |
| Input $ / M tokens | $0.60 | $1.25 |
| Output $ / M tokens | $2.20 | $2.50 |
| Results tracked | 36 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 44.0 (#79), Grok 4.3: 41.6 (#121)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| LMArena WebDev | 1435 | 1357 |
| SciCode | 45.1% | 47.3% |
| LMArena Coding | 1454 | 1415 |
| ALE-Bench | 399.48 | 944.17 |
| WeirdML | — | 49.9% |
Agentic & Tool Use Grok 4.3 leads
GLM-4.7: 26.5 (#103), Grok 4.3: 27.7 (#99)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| Vending-Bench 2 | 2,377 | 35.26 |
| Terminal-Bench | 33.4% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
Reasoning Grok 4.3 leads
GLM-4.7: 24.3 (#164), Grok 4.3: 35.9 (#68)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| CritPt | 1.7% | 8% |
| Chess Puzzles | 6% | 25% |
| LMArena Hard Prompts | 1443 | 1396 |
| Epoch Capabilities Index | 143.51 | 149.16 |
| SimpleBench | 47.7% | — |
| NYT Connections (extended) | — | 55.2% |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
| ForecastBench | — | 60.3 |
Math Grok 4.3 leads
GLM-4.7: 38.6 (#135), Grok 4.3: 46.0 (#74)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 93.3% |
| ProofBench | 6% | 11% |
| LMArena Math | 1423 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 4.3 leads
GLM-4.7: 47.0 (#80), Grok 4.3: 52.5 (#62)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 83.3% | 88.8% |
| SimpleQA Verified | 32.2% | 33.2% |
| LMArena Expert | 1424 | 1385 |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, Grok 4.3: 31.6 (#104)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual GLM-4.7 leads
GLM-4.7: 52.8 (#79), Grok 4.3: 50.5 (#120)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1417 | 1385 |
| LMArena Chinese | 1495 | 1422 |
| LMArena French | 1432 | 1412 |
| LMArena German | 1424 | 1395 |
| LMArena Japanese | 1439 | 1379 |
| LMArena Korean | 1399 | 1356 |
| LMArena Russian | 1423 | 1399 |
| LMArena Spanish | 1434 | 1398 |
Instruction Following GLM-4.7 leads
GLM-4.7: 74.4 (#95), Grok 4.3: 72.1 (#140)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1411 | 1366 |
Long Context Too close to call
GLM-4.7: 42.8 (#116), Grok 4.3: 42.5 (#123)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1432 | 1393 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-4.7 leads
GLM-4.7: 60.9 (#93), Grok 4.3: 58.5 (#118)
| Benchmark | GLM-4.7 | Grok 4.3 |
|---|---|---|
| LMArena Text | 1435 | 1397 |
| LMArena Creative Writing | 1401 | 1380 |
| LMArena Multi-Turn | 1446 | 1406 |
| EQ-Bench Creative Writing | 1413 | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is GLM-4.7 better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 42.0 on the Noometry Index. GLM-4.7 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-4.7 or Grok 4.3?
GLM-4.7 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-4.7 or Grok 4.3 better for coding?
GLM-4.7 scores higher on coding benchmarks: 44.0 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-4.7 and Grok 4.3 share?
28 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Grok 4.3 has 40.