Model comparison
Claude Opus 4.1 vs GLM-4.7
Claude Opus 4.1 and GLM-4.7 score almost the same on the Noometry Index (41.0 vs 42.0), so choose on price, context window or the category you care about most.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Claude Opus 4.1 scores higher in 6 categories and GLM-4.7 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.7 leads 38.6 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.9% for Claude Opus 4.1 and 83.3% for GLM-4.7.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GLM-4.7 accepts more context: 205K tokens versus 200K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | GLM-4.7 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 41.0 | 42.0 |
| Released | 2025-08-05 | 2025-12-22 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 32K | 131K |
| Input $ / M tokens | $15 | $0.60 |
| Output $ / M tokens | $75 | $2.20 |
| Results tracked | 48 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4.1: 44.4 (#73), GLM-4.7: 44.0 (#79)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| LMArena WebDev | 1390 | 1435 |
| LMArena Coding | 1479 | 1454 |
| ALE-Bench | 674.77 | 399.48 |
| SWE-bench Verified | 73.3% | — |
| SciCode | — | 45.1% |
| WeirdML | 45.9% | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), GLM-4.7: 26.5 (#103)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| Terminal-Bench | 38% | 33.4% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 2,377 |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), GLM-4.7: 24.3 (#164)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| SimpleBench | 60% | 47.7% |
| Chess Puzzles | 7% | 6% |
| LMArena Hard Prompts | 1443 | 1443 |
| Epoch Capabilities Index | 144.12 | 143.51 |
| CritPt | — | 1.7% |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 80% | — |
| LMCA | 37.1% | — |
| ForecastBench | 62 | — |
Math GLM-4.7 leads
Claude Opus 4.1: 22.3 (#277), GLM-4.7: 38.6 (#135)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 83.3% |
| LMArena Math | 1431 | 1423 |
| FrontierMath (Feb 2025 set) | 7.2% | 2.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | — | 6% |
Knowledge GLM-4.7 leads
Claude Opus 4.1: 42.0 (#101), GLM-4.7: 47.0 (#80)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| GPQA Diamond | 77.3% | 83.3% |
| Vectara Hallucination Rate | 11.8% | 11.7% |
| LMArena Expert | 1439 | 1424 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 32.2% |
| Confabulations | 17.1% | — |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), GLM-4.7: —
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| VPCT | 35% | — |
Multilingual Too close to call
Claude Opus 4.1: 52.0 (#95), GLM-4.7: 52.8 (#79)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| LMArena Non-English | 1405 | 1417 |
| LMArena Chinese | 1427 | 1495 |
| LMArena French | 1431 | 1432 |
| LMArena German | 1413 | 1424 |
| LMArena Japanese | 1378 | 1439 |
| LMArena Korean | 1380 | 1399 |
| LMArena Russian | 1422 | 1423 |
| LMArena Spanish | 1448 | 1434 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), GLM-4.7: 74.4 (#95)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1411 |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#63), GLM-4.7: 42.8 (#116)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| LMArena Longer Query | 1455 | 1432 |
| CL-bench | — | 15.9% |
| CL-bench Life | — | 10.9% |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.4 (#74), GLM-4.7: 60.9 (#93)
| Benchmark | Claude Opus 4.1 | GLM-4.7 |
|---|---|---|
| LMArena Text | 1419 | 1435 |
| LMArena Creative Writing | 1412 | 1401 |
| LMArena Multi-Turn | 1444 | 1446 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1413 |
Frequently asked questions
Is Claude Opus 4.1 better than GLM-4.7?
Claude Opus 4.1 and GLM-4.7 score almost the same on the Noometry Index (41.0 vs 42.0), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Opus 4.1 or GLM-4.7?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or GLM-4.7 better for coding?
They score almost the same on coding (44.4 vs 44.0); test both on your own repository before choosing.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 200K.
How many benchmarks do Claude Opus 4.1 and GLM-4.7 share?
28 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GLM-4.7 has 36.