Model comparison
GLM-4.7-Flash vs o3
o3 is the stronger model overall, scoring 47.5 to 38.8 on the Noometry Index. GLM-4.7-Flash costs 24× less per token, which makes it the better buy when o3'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 o3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 35.5.
- The biggest single-benchmark swing is Chess Puzzles: 0% for GLM-4.7-Flash and 38% for o3.
- GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $2 / $8 for o3.
- GLM-4.7-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7-Flash | o3 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 38.8 | 47.5 |
| Released | 2026-01-19 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 200K | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $0.06 | $2 |
| Output $ / M tokens | $0.40 | $8 |
| Results tracked | 21 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
GLM-4.7-Flash: 40.6 (#135), o3: 46.8 (#64)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| LMArena Coding | 1383 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
GLM-4.7-Flash: —, o3: 34.5 (#44)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
GLM-4.7-Flash: 20.9 (#229), o3: 32.0 (#78)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| Chess Puzzles | 0% | 38% |
| LMArena Hard Prompts | 1356 | 1402 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
GLM-4.7-Flash: 36.1 (#173), o3: 50.2 (#58)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 58.3% | 84.4% |
| LMArena Math | 1355 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
GLM-4.7-Flash: 35.5 (#184), o3: 54.6 (#52)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| GPQA Diamond | 60.5% | 81.8% |
| LMArena Expert | 1357 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 75.3% |
Multimodal Not comparable
GLM-4.7-Flash: —, o3: 41.4 (#36)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
GLM-4.7-Flash: 46.5 (#158), o3: 51.7 (#105)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| LMArena Non-English | 1330 | 1401 |
| LMArena Chinese | 1403 | 1437 |
| LMArena French | 1332 | 1430 |
| LMArena German | 1337 | 1420 |
| LMArena Korean | 1283 | 1370 |
| LMArena Russian | 1332 | 1406 |
| LMArena Spanish | 1350 | 1395 |
| LMArena Japanese | — | 1403 |
Instruction Following o3 leads
GLM-4.7-Flash: 70.1 (#167), o3: 72.8 (#127)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| LMArena Instruction Following | 1327 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
GLM-4.7-Flash: 40.9 (#148), o3: 53.3 (#6)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| LMArena Longer Query | 1345 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
GLM-4.7-Flash: 47.4 (#210), o3: 63.5 (#64)
| Benchmark | GLM-4.7-Flash | o3 |
|---|---|---|
| LMArena Text | 1351 | 1410 |
| LMArena Creative Writing | 1297 | 1359 |
| EQ-Bench Creative Writing | 1125 | 1676 |
| LMArena Multi-Turn | 1342 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |
Frequently asked questions
Is GLM-4.7-Flash better than o3?
o3 is the stronger model overall, scoring 47.5 to 38.8 on the Noometry Index. GLM-4.7-Flash costs 24× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7-Flash or o3?
GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; o3 lists at $2 and $8.
Is GLM-4.7-Flash or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 40.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do GLM-4.7-Flash and o3 share?
20 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and o3 has 63.