Model comparison
GLM-4.6V vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 40.9 on the Noometry Index. GLM-4.6V costs 3.5× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 1 category and Grok 4.20 (Non-Reasoning) in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 26.5.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6V | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 40.9 | 48.5 |
| Released | 2025-12-08 | 2026-02-17 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 33K | 30K |
| Input $ / M tokens | $0.30 | $1.25 |
| Output $ / M tokens | $0.90 | $2.50 |
| Results tracked | 12 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 40.2 (#128), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Coding | 1390 | 1458 |
| LMArena WebDev | — | 1374 |
| WeirdML | — | 52.3% |
| ALE-Bench | — | 1,150 |
Agentic & Tool Use Not comparable
GLM-4.6V: —, Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 26.5 (#117), Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1451 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| Epoch Capabilities Index | — | 152.01 |
| ForecastBench | — | 61.4 |
Math Not comparable
GLM-4.6V: —, Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | — | 14% |
| LMArena Math | — | 1455 |
Knowledge Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 37.4 (#148), Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Expert | 1372 | 1440 |
| GPQA Diamond | — | 89.3% |
| SimpleQA Verified | — | 30.2% |
Multimodal Too close to call
GLM-4.6V: 34.2 (#83), Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1164 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 48.8 (#135), Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1359 | 1440 |
| LMArena Chinese | 1426 | 1481 |
| LMArena Russian | 1341 | 1457 |
| LMArena French | — | 1477 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1450 |
| LMArena Korean | — | 1417 |
| LMArena Spanish | — | 1442 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 71.6 (#145), Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1351 | 1420 |
Long Context Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 41.3 (#138), Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1358 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
GLM-4.6V: 56.8 (#132), Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | GLM-4.6V | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1377 | 1451 |
| LMArena Creative Writing | 1347 | 1439 |
| LMArena Multi-Turn | 1359 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |
Frequently asked questions
Is GLM-4.6V better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 40.9 on the Noometry Index. GLM-4.6V costs 3.5× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, GLM-4.6V or Grok 4.20 (Non-Reasoning)?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is GLM-4.6V or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 40.2 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.
How many benchmarks do GLM-4.6V and Grok 4.20 (Non-Reasoning) share?
12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.