Model comparison
GLM-5 vs o4-mini
GLM-5 is the stronger model overall, scoring 46.1 to 41.6 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. GLM-5 scores higher in 7 categories and o4-mini in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.0 to 54.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 72.8% for GLM-5 and 45% for o4-mini.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- GLM-5 accepts more context: 205K tokens versus 200K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | o4-mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 41.6 |
| Released | 2026-02-11 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1 | $1.10 |
| Output $ / M tokens | $3.20 | $4.40 |
| Results tracked | 45 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), o4-mini: 40.9 (#127)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 45% |
| WeirdML | 48.2% | 52.6% |
| LMArena Coding | 1461 | 1368 |
| ALE-Bench | 765.62 | 826.17 |
| SWE-bench Verified | 72.1% | — |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
GLM-5: 31.1 (#71), o4-mini: 32.6 (#61)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), o4-mini: 24.6 (#162)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 4.9% | 6.1% |
| SimpleBench | 53.2% | 38.7% |
| Kagi LLM Benchmark | 75% | 67.6% |
| ARC-AGI-1 | 44.7% | 58.7% |
| Chess Puzzles | 10% | 26% |
| LMArena Hard Prompts | 1452 | 1351 |
| Epoch Capabilities Index | 145.83 | 145.64 |
| ForecastBench | 61 | 61.8 |
| NYT Connections (extended) | 74.8% | — |
| CritPt | — | 0.6% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
Math GLM-5 leads
GLM-5: 46.4 (#71), o4-mini: 40.8 (#89)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 81.7% |
| LMArena Math | 1440 | 1389 |
| FrontierMath (Feb 2025 set) | 16.4% | 24.8% |
| FrontierMath Tier 4 (v1) | 2.1% | 6.3% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| MathArena Final-Answer Competitions | 65.7% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), o4-mini: 43.6 (#91)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| GPQA Diamond | 87.8% | 79.6% |
| Vectara Hallucination Rate | 10.1% | 18.6% |
| LMArena Expert | 1454 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal Not comparable
GLM-5: —, o4-mini: 40.2 (#49)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), o4-mini: 47.0 (#154)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| LMArena Non-English | 1430 | 1337 |
| LMArena Chinese | 1511 | 1354 |
| LMArena French | 1455 | 1364 |
| LMArena German | 1445 | 1336 |
| LMArena Japanese | 1416 | 1308 |
| LMArena Korean | 1423 | 1312 |
| LMArena Russian | 1436 | 1334 |
| LMArena Spanish | 1454 | 1347 |
Instruction Following Too close to call
GLM-5: 75.2 (#67), o4-mini: 75.2 (#68)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1428 | 1321 |
| IFEval | — | 92.8% |
Long Context Too close to call
GLM-5: 44.7 (#60), o4-mini: 45.5 (#33)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1446 | 1315 |
| Fiction.LiveBench | — | 77.8% |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), o4-mini: 54.0 (#152)
| Benchmark | GLM-5 | o4-mini |
|---|---|---|
| LMArena Text | 1446 | 1353 |
| LMArena Creative Writing | 1439 | 1294 |
| LMArena Multi-Turn | 1456 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1601 | — |
| WildBench | — | 85.4% |
Frequently asked questions
Is GLM-5 better than o4-mini?
GLM-5 is the stronger model overall, scoring 46.1 to 41.6 on the Noometry Index.
Which is cheaper, GLM-5 or o4-mini?
GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is GLM-5 or o4-mini better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 200K.
How many benchmarks do GLM-5 and o4-mini share?
32 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and o4-mini has 60.