Model comparison
GLM-4.6 vs Grok 4.7
Grok 4.7 is the stronger model overall, scoring 53.1 to 41.4 on the Noometry Index. GLM-4.6 costs 3.0× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GLM-4.6 scores higher in 3 categories and Grok 4.7 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.7 leads 49.1 to 23.7.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 57.8% for Grok 4.7.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Grok 4.7 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 53.1 |
| Released | 2025-09-30 | 2026-09-21 |
| Weights | Open | Proprietary |
| Context window | 205K | 500K |
| Max output | 131K | 500K |
| Input $ / M tokens | $0.60 | $2 |
| Output $ / M tokens | $2.20 | $6 |
| Results tracked | 29 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
GLM-4.6: 40.1 (#148), Grok 4.7: 58.0 (#18)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena WebDev | 1340 | 1639 |
| SciCode | 38.4% | 57.8% |
| LMArena Coding | 1449 | 1427 |
| FrontierCode | — | 47.6% |
| SWE-bench Verified (bash only) | 55.4% | — |
| CursorBench | — | 46.3% |
| FrontierSWE | — | 29.5% |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Grok 4.7 leads
GLM-4.6: 32.3 (#66), Grok 4.7: 36.7 (#37)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| APEX-Agents | — | 54.6% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| GDP.pdf | — | 22.8% |
| Vending-Bench 2 | — | 10,537 |
Reasoning Grok 4.7 leads
GLM-4.6: 23.7 (#172), Grok 4.7: 49.1 (#40)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| CritPt | 1.1% | 18% |
| LMArena Hard Prompts | 1440 | 1413 |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 76.8% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 96% |
| LMCA | — | 49.4% |
| Epoch Capabilities Index | — | 153.53 |
Math Grok 4.7 leads
GLM-4.6: 39.1 (#111), Grok 4.7: 57.8 (#39)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Math | 1432 | 1407 |
| FrontierMath (Tiers 1-3) | — | 53% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 98.1% |
| ProofBench | — | 34% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4.7 leads
GLM-4.6: 40.2 (#124), Grok 4.7: 62.8 (#22)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Expert | 1431 | 1422 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 56% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Grok 4.7: 35.5 (#87)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Vision | — | 1228 |
| Blueprint-Bench 2 | — | 32.5% |
| Furniture Assembly | — | 20.8% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.5 (#66), Grok 4.7: 50.8 (#116)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1426 | 1389 |
| LMArena Chinese | 1499 | 1455 |
| LMArena French | 1459 | 1455 |
| LMArena Russian | 1419 | 1397 |
| LMArena Spanish | 1436 | 1400 |
| LMArena German | 1447 | — |
| LMArena Japanese | 1393 | — |
| LMArena Korean | 1400 | — |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Grok 4.7: 74.1 (#105)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1404 |
Long Context Too close to call
GLM-4.6: 43.4 (#94), Grok 4.7: 43.1 (#104)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1422 | 1413 |
Writing & Preference Grok 4.7 leads
GLM-4.6: 61.1 (#90), Grok 4.7: 70.0 (#24)
| Benchmark | GLM-4.6 | Grok 4.7 |
|---|---|---|
| LMArena Text | 1440 | 1399 |
| LMArena Creative Writing | 1411 | 1391 |
| EQ-Bench Creative Writing | 1411 | 2007 |
| LMArena Multi-Turn | 1427 | 1393 |
Frequently asked questions
Is GLM-4.6 better than Grok 4.7?
Grok 4.7 is the stronger model overall, scoring 53.1 to 41.4 on the Noometry Index. GLM-4.6 costs 3.0× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or Grok 4.7?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Grok 4.7 lists at $2 and $6.
Is GLM-4.6 or Grok 4.7 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.7 does, with 500K tokens against 205K.
How many benchmarks do GLM-4.6 and Grok 4.7 share?
18 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Grok 4.7 has 39.