GLM-4.7
| Released | 2025-12-22 |
|---|---|
| Price per 1M | $0.45 in · $2.09 out |
| Overall score | 50.1 · rank 111 |
| Context window | 204,800 tokens |
| Provider | Zhipu AI |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 50.1 | 111 | 19 |
| Overall: Coding | 50.5 | 105 | 10 |
| Overall: Reasoning | 49.0 | 122 | 10 |
| Overall: Agentic work | 49.8 | 114 | 9 |
| Overall: Frontend | 48.1 | 111 | 4 |
| Coding | 52.4 | 100 | 3 |
| Agents | 48.6 | 114 | 2 |
| Reasoning | 50.6 | 109 | 4 |
| Math | 46.6 | 140 | 4 |
| Knowledge | 49.5 | 96 | 2 |
| Frontend | 45.9 | 87 | 1 |
| General | 52.8 | 81 | 3 |
| Value vs price | +2.8 | 97 |
Evidence
Coding 52.4 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SciCode | 45.1% | Epoch AI | 2026-11-11 |
| SWE-bench Verified (Vals run) | 69.4% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 82.2% | Vals AI | 2026-09-01 |
Agents 48.6 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 33.4% | Epoch AI | 2025-12-22 |
| Vending-Bench 2 | $2,377 | Epoch AI | 2026-11-11 |
Reasoning 50.6 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 1.7% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 83.3% | Epoch AI | 2026-01-29 |
| GPQA Diamond (Vals run) | 80.1% | Vals AI | 2026-09-01 |
| Chess Puzzles | 21.0% | Epoch AI | 2026-10-14 |
| SimpleBench | 47.7% | SimpleBench | 2025-12-23 |
| SimpleBench | 47.7% | Epoch AI | 2026-11-11 |
Math 46.6 ±4.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 2.4% | Epoch AI | 2026-01-30 |
| ProofBench | 6.0% | Epoch AI | 2026-11-11 |
| FrontierMath Tier 4 (2025 set) | 0.0% | Epoch AI | 2026-01-30 |
| OTIS Mock AIME 2024-2025 | 83.3% | Epoch AI | 2026-01-29 |
Knowledge 49.5 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 32.2% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 82.7% | Vals AI | 2026-09-01 |
Frontend 45.9 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,435 | LMArena | 2026-11-09 |
General 52.8 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,441 | LMArena | 2026-11-09 |
| EQ-Bench Creative Writing v3 | 1,414 | EQ-Bench | 2026-11-11 |
| EQ-Bench Longform Creative Writing | 66.0% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Terminal-Bench 2.0 | 33.3% | Epoch AI | A stronger configuration result was used |
Names matched to this model
glm-4-7, glm-4p7