Model comparison
GLM-5.3-Flash vs Grok 4.20 (Non-Reasoning)
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 48.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GLM-5.3-Flash scores higher in 7 categories and Grok 4.20 (Non-Reasoning) in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 31.7.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 55.8% for GLM-5.3-Flash and 44.9% for Grok 4.20 (Non-Reasoning).
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | Z.ai (Zhipu) | xAI |
| Noometry Index | 49.6 | 48.5 |
| Released | 2026-08-20 | 2026-02-17 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 131K | 30K |
| Input $ / M tokens | $0.15 | $1.25 |
| Output $ / M tokens | $0.50 | $2.50 |
| Results tracked | 36 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.7 (#26), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1614 | 1374 |
| LMArena Coding | 1506 | 1458 |
| ALE-Bench | 303.55 | 1,150 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| SciCode | 51.6% | — |
| WeirdML | — | 52.3% |
Agentic & Tool Use Too close to call
GLM-5.3-Flash: 34.3 (#41), Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| APEX-Agents | 52.8% | — |
| τ²-bench Banking | — | 18% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
GLM-5.3-Flash: 31.7 (#69), Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Chess Puzzles | 14% | 24% |
| LMArena Hard Prompts | 1490 | 1451 |
| Epoch Capabilities Index | 151.9 | 152.01 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| CritPt | 15.4% | — |
| Thematic Generalization | — | 63.8% |
| Mystery Game Puzzles | 8% | — |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| ForecastBench | — | 61.4 |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#38), Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 44.9% |
| FrontierMath Tier 4 | 17.1% | 17.1% |
| OTIS Mock AIME 2024-2025 | 93.9% | 92.2% |
| ProofBench | 21% | 14% |
| LMArena Math | 1499 | 1455 |
Knowledge GLM-5.3-Flash leads
GLM-5.3-Flash: 58.4 (#33), Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 90.2% | 89.3% |
| LMArena Expert | 1512 | 1440 |
| SimpleQA Verified | — | 30.2% |
Multimodal GLM-5.3-Flash leads
GLM-5.3-Flash: 42.6 (#25), Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1304 | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual GLM-5.3-Flash leads
GLM-5.3-Flash: 56.2 (#24), Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1462 | 1440 |
| LMArena Chinese | 1529 | 1481 |
| LMArena French | 1495 | 1477 |
| LMArena German | 1457 | 1463 |
| LMArena Japanese | 1420 | 1450 |
| LMArena Korean | 1443 | 1417 |
| LMArena Russian | 1472 | 1457 |
| LMArena Spanish | 1471 | 1442 |
Instruction Following GLM-5.3-Flash leads
GLM-5.3-Flash: 77.8 (#17), Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1480 | 1420 |
Long Context Too close to call
GLM-5.3-Flash: 45.3 (#41), Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1479 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Too close to call
GLM-5.3-Flash: 65.4 (#49), Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | GLM-5.3-Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1471 | 1451 |
| LMArena Creative Writing | 1440 | 1439 |
| LMArena Multi-Turn | 1471 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |
Frequently asked questions
Is GLM-5.3-Flash better than Grok 4.20 (Non-Reasoning)?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 48.5 on the Noometry Index.
Which is cheaper, GLM-5.3-Flash or Grok 4.20 (Non-Reasoning)?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is GLM-5.3-Flash or Grok 4.20 (Non-Reasoning) better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do GLM-5.3-Flash and Grok 4.20 (Non-Reasoning) share?
27 benchmarks have published results for both models. GLM-5.3-Flash has 36 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.