GLM-5.2
| Released | 2026-06-13 |
|---|---|
| Price per 1M | $1.20 in · $4.18 out |
| Overall score | 56.6 · rank 61 |
| Context window | 1,000,000 tokens |
| Provider | Zhipu AI |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 56.6 | 61 | 39 |
| Overall: Coding | 56.3 | 61 | 25 |
| Overall: Reasoning | 56.0 | 66 | 17 |
| Overall: Agentic work | 57.0 | 60 | 23 |
| Overall: Frontend | 55.5 | 58 | 10 |
| Coding | 56.2 | 63 | 8 |
| Agents | 57.5 | 56 | 6 |
| Reasoning | 56.4 | 74 | 9 |
| Math | 56.8 | 57 | 5 |
| Knowledge | 53.6 | 72 | 3 |
| Frontend | 55.1 | 54 | 2 |
| General | 59.8 | 31 | 6 |
| Value vs price | +6.9 | 54 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 53.8 ±1.9 | 13 |
| High | 57.0 ±4.1 | 3 |
| Low | 54.9 ±6.0 | 5 |
| Max | 57.1 ±1.2 | 22 |
| Medium | 50.9 ±12.0 | 1 |
| Minimal | 52.9 ±12.0 | 1 |
| Non-reasoning | 51.9 ±3.5 | 8 |
| Thinking | 48.5 ±9.4 | 1 |
| Extra High | 58.8 ±6.1 | 1 |
Evidence
Coding 56.2 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 43.8% | Epoch AI | 2026-11-11 |
| FrontierCode | 24.5% | Epoch AI | 2026-11-11 |
| SWE-rebench | 62.9% | SWE-rebench | 2026-07-01 |
| MirrorCode | 36.7% | Epoch AI | 2026-10-21 |
| SciCode | 51.2% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 69.5% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 78.7% | Epoch AI | 2026-06-25 |
| ProgramBench | 0.5% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 82.8% | Vals AI | 2026-09-01 |
Agents 57.5 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SRE Bench | 0.0% | Vals AI | 2026-11-05 |
| APEX-Agents | 45.2% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.1 (Vals run) | 67.8% | Vals AI | 2026-10-01 |
| tau2-bench Banking Knowledge | 37.1% | tau2-bench | 2026-07-24 |
| SkillsBench | 45.1% | Vals AI | 2026-10-29 |
| Vending-Bench 2 | $8,314 | Epoch AI | 2026-11-11 |
Reasoning 56.4 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 22.8% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 74.3% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 (ARC Prize verified) | 22.8% | ARC Prize | 2026-11-11 |
| CritPt | 20.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 77.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 77.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 91.9% | Epoch AI | 2026-06-24 |
| GPQA Diamond (Vals run) | 85.6% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 62.6% | Kagi | 2026-11-11 |
| Chess Puzzles | 22.0% | Epoch AI | 2026-10-14 |
| SimpleBench | 58.8% | SimpleBench | 2026-06-17 |
| SimpleBench | 58.8% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 19.0% | Epoch AI | 2026-08-27 |
Math 56.8 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 59.2% | Epoch AI | 2026-06-19 |
| FrontierMath Tier 4 | 29.3% | Epoch AI | 2026-06-19 |
| ProofBench | 35.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 86.4% | Epoch AI | 2026-06-25 |
| MathArena Final-Answer Competitions | 67.6% | MathArena | 2026-11-11 |
Knowledge 53.6 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 34.2% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 86.7% | Vals AI | 2026-09-01 |
| Legal Research Bench | 31.3% | Vals AI | 2026-11-09 |
Frontend 55.1 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 64.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,608 | LMArena | 2026-11-09 |
General 59.8 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,556 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,208 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,759 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,475 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 56.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 77.9% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Chess Puzzles | 19.0% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 18.0% | Epoch AI | A stronger configuration result was used |
| CritPt | 3.1% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 36.3% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 | 42.5% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 | 54.7% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 71.2% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 87.9% | Epoch AI | A stronger configuration result was used |
| Kagi Reasoning Benchmark | 60.0% | Kagi | A stronger configuration result was used |
| Mystery Game Puzzles | 18.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 15.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 18.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 28.9% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 75.6% | Epoch AI | A stronger configuration result was used |
| SciCode | 36.1% | Epoch AI | A stronger configuration result was used |
Names matched to this model
glm-5-2