Model comparison
GLM-5V-Turbo vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 43.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. GLM-5V-Turbo scores higher in 4 categories and GPT-5.4 mini in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 39.9.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GPT-5.4 mini accepts more context: 400K tokens versus 200K.
Side by side
| GLM-5V-Turbo | GPT-5.4 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 43.1 | 44.8 |
| Released | 2026-04-01 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.20 | $0.75 |
| Output $ / M tokens | $4 | $4.50 |
| Results tracked | 19 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GLM-5V-Turbo: 41.8 (#105), GPT-5.4 mini: 45.0 (#67)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena WebDev | 1400 | 1397 |
| LMArena Coding | 1467 | 1438 |
| FrontierCode | — | 27% |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Not comparable
GLM-5V-Turbo: —, GPT-5.4 mini: 29.6 (#74)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
GLM-5V-Turbo: 28.5 (#87), GPT-5.4 mini: 30.3 (#77)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1424 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LMCA | — | 40.8% |
| Epoch Capabilities Index | — | 148.83 |
| ForecastBench | — | 57 |
Math GPT-5.4 mini leads
GLM-5V-Turbo: 36.6 (#109), GPT-5.4 mini: 45.4 (#63)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Math | 1440 | 1418 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 21% |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
GLM-5V-Turbo: 39.9 (#113), GPT-5.4 mini: 51.4 (#62)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Expert | 1451 | 1434 |
| GPQA Diamond | — | 86.9% |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
Multimodal GLM-5V-Turbo leads
GLM-5V-Turbo: 40.1 (#41), GPT-5.4 mini: 39.0 (#51)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1264 | 1245 |
| LMArena Document | 1416 | — |
Multilingual GLM-5V-Turbo leads
GLM-5V-Turbo: 53.2 (#69), GPT-5.4 mini: 52.1 (#94)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1420 | 1405 |
| LMArena Chinese | 1488 | 1446 |
| LMArena French | 1443 | 1440 |
| LMArena German | 1422 | 1407 |
| LMArena Korean | 1399 | 1369 |
| LMArena Russian | 1432 | 1417 |
| LMArena Spanish | 1446 | 1403 |
| LMArena Japanese | — | 1375 |
Instruction Following Too close to call
GLM-5V-Turbo: 75.1 (#75), GPT-5.4 mini: 74.3 (#99)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1422 | 1405 |
Long Context GLM-5V-Turbo leads
GLM-5V-Turbo: 44.0 (#76), GPT-5.4 mini: 42.9 (#107)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1439 | 1407 |
Writing & Preference GPT-5.4 mini leads
GLM-5V-Turbo: 62.6 (#69), GPT-5.4 mini: 64.2 (#56)
| Benchmark | GLM-5V-Turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1437 | 1411 |
| LMArena Creative Writing | 1414 | 1370 |
| LMArena Multi-Turn | 1432 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
Frequently asked questions
Is GLM-5V-Turbo better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 44.8 to 43.1 on the Noometry Index.
Which is cheaper, GLM-5V-Turbo or GPT-5.4 mini?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is GLM-5V-Turbo or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 200K.
How many benchmarks do GLM-5V-Turbo and GPT-5.4 mini share?
18 benchmarks have published results for both models. GLM-5V-Turbo has 19 scored results on Noometry and GPT-5.4 mini has 46.