Model comparison
GLM-4.7-Flash vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 38.4 on the Noometry Index. GLM-4.7-Flash costs 13× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GLM-4.7-Flash scores higher in 0 categories and o4-mini in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.5 to 35.4.
- The biggest single-benchmark swing is Chess Puzzles: 0% for GLM-4.7-Flash and 26% for o4-mini.
- GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- GLM-4.7-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7-Flash | o4-mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.4 | 41.6 |
| Released | 2026-01-19 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 200K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $0.06 | $1.10 |
| Output $ / M tokens | $0.40 | $4.40 |
| Results tracked | 21 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
GLM-4.7-Flash: 40.0 (#133), o4-mini: 41.6 (#110)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| LMArena Coding | 1383 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
GLM-4.7-Flash: —, o4-mini: 32.3 (#57)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
GLM-4.7-Flash: 20.2 (#224), o4-mini: 24.6 (#143)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| Chess Puzzles | 0% | 26% |
| LMArena Hard Prompts | 1356 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.63 |
| ForecastBench | — | 61.8 |
Math o4-mini leads
GLM-4.7-Flash: 34.4 (#159), o4-mini: 40.2 (#79)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 81.7% |
| LMArena Math | 1354 | 1390 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
GLM-4.7-Flash: 35.4 (#177), o4-mini: 43.5 (#83)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| GPQA Diamond | 60.5% | 79.6% |
| Vectara Hallucination Rate | 9.3% | 18.6% |
| LMArena Expert | 1357 | 1344 |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |
Multimodal Not comparable
GLM-4.7-Flash: —, o4-mini: 39.5 (#46)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Too close to call
GLM-4.7-Flash: 46.8 (#152), o4-mini: 47.2 (#149)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| LMArena Non-English | 1331 | 1336 |
| LMArena Chinese | 1403 | 1355 |
| LMArena French | 1332 | 1362 |
| LMArena German | 1336 | 1336 |
| LMArena Korean | 1284 | 1313 |
| LMArena Russian | 1333 | 1334 |
| LMArena Spanish | 1351 | 1346 |
| LMArena Japanese | — | 1308 |
Instruction Following o4-mini leads
GLM-4.7-Flash: 70.3 (#162), o4-mini: 75.4 (#63)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1327 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
GLM-4.7-Flash: 40.9 (#143), o4-mini: 45.5 (#31)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| LMArena Longer Query | 1345 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
GLM-4.7-Flash: 47.7 (#206), o4-mini: 54.2 (#148)
| Benchmark | GLM-4.7-Flash | o4-mini |
|---|---|---|
| LMArena Text | 1351 | 1353 |
| LMArena Creative Writing | 1297 | 1294 |
| LMArena Multi-Turn | 1342 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1125 | — |
| WildBench | — | 85.4% |
Frequently asked questions
Is GLM-4.7-Flash better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 38.4 on the Noometry Index. GLM-4.7-Flash costs 13× less per token, which makes it the better buy when o4-mini's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7-Flash or o4-mini?
GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is GLM-4.7-Flash or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 41.6 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do GLM-4.7-Flash and o4-mini share?
20 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and o4-mini has 60.