Model comparison
GLM-4.6 vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 41.4 on the Noometry Index. GLM-4.6 costs 1.6× 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 . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 23.7.
- The biggest single-benchmark swing is Terminal-Bench: 24.5% for GLM-4.6 and 57.3% for Grok 4.20 (Non-Reasoning).
- GLM-4.6 is cheaper at $0.60 / $2.20 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 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 41.4 | 48.6 |
| Released | 2025-09-30 | 2026-02-17 |
| 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 | 29 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 40.1 (#148), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1340 | 1375 |
| LMArena Coding | 1449 | 1459 |
| ALE-Bench | 340.82 | 1,150 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| WeirdML | — | 52.3% |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 32.3 (#66), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | 24.5% | 57.3% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 23.7 (#172), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 75% |
| LMArena Hard Prompts | 1440 | 1451 |
| ARC-AGI-2 | — | 65.1% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| Epoch Capabilities Index | — | 151.98 |
| ForecastBench | — | 61.4 |
Math Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 39.1 (#111), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Math | 1432 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | — | 14% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 40.2 (#124), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Expert | 1431 | 1439 |
| GPQA Diamond | — | 89.3% |
| SimpleQA Verified | — | 30.2% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 53.5 (#66), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1426 | 1441 |
| LMArena Chinese | 1499 | 1481 |
| LMArena French | 1459 | 1476 |
| LMArena German | 1447 | 1465 |
| LMArena Japanese | 1393 | 1449 |
| LMArena Korean | 1400 | 1417 |
| LMArena Russian | 1419 | 1458 |
| LMArena Spanish | 1436 | 1443 |
Instruction Following Too close to call
GLM-4.6: 74.3 (#98), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1410 | 1420 |
Long Context Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 43.4 (#94), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1422 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
GLM-4.6: 61.1 (#90), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | GLM-4.6 | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1440 | 1451 |
| LMArena Creative Writing | 1411 | 1438 |
| EQ-Bench Creative Writing | 1411 | 1574 |
| LMArena Multi-Turn | 1427 | 1456 |
Frequently asked questions
Is GLM-4.6 better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 41.4 on the Noometry Index. GLM-4.6 costs 1.6× 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-4.6 or Grok 4.20 (Non-Reasoning)?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is GLM-4.6 or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 205K.
How many benchmarks do GLM-4.6 and Grok 4.20 (Non-Reasoning) share?
22 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.