- AIME 25 93.9
- GPQA 81
- LiveCodeBench v6 82.8
- Best of HLE / HLE (w/ Tools) 30.4
- BrowseComp 45.1
- SWE-bench Verified 68
- Terminal-Bench 40.5
- τ²-Bench (Weighted) 75.9
GLM-4.6
GLM-4.6.
47
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Z.ai Sep 2025
GLM-4.6
Open weights Flagship
No Epoch Capabilities Index score yet
- SWE-Bench Pro 9.67% #23 /24
- Terminal-Bench 2.0 24.5% #38 /43
- Toolathlon 18.8% #39 /50
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,424 | #101 of 333 | Official leaderboard | |
| Creative Writing v3 | 69.3 | #58 of 120 | Official leaderboard | |
| Humanity's Last Exam | 30.4% | #75 of 147 | Model card | |
| Vectara Hallucination Leaderboard (2025 dataset) | 9.50% | #54 of 104 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 4.30% | #78 of 148 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 57.3 | #73 of 119 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HMMT 2025 | 93.3% | #8 of 53 | Official leaderboard | |
| AIME 2025 | 93.9% | #29 of 143 | Model card | |
| SMT 2025 | 90.6% | #9 of 40 | Official leaderboard | |
| BRUMO 2025 | 94.2% | #14 of 42 | Official leaderboard | |
| CMIMC 2025 | 87.5% | #11 of 33 | Official leaderboard | |
| HMMT Nov 2025 | 91.7% | #8 of 22 | Official leaderboard | |
| GPQA Diamond | 81% | #105 of 284 | Model card | |
| CritPt | 1.14% | #92 of 160 | Epoch AI | |
| General365 | 52.9% | #14 of 23 | Official leaderboard | |
| FrontierMath Tier 4 | 2.13% | #36 of 55 | Epoch AI | |
| FrontierMath | 3.82% | #51 of 70 | Epoch AI | |
| MathArena (Apex, IMO, USAMO) | 0.52% | #45 of 47 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 68.2% | #17 of 60 | Official leaderboard | |
| LiveCodeBench v6 | 82.8% | #24 of 76 | Model card | |
| SWE-fficiency | 4.20% | #13 of 17 | Official leaderboard | |
| WebDev Arena | 1,341 | #83 of 105 | Epoch AI | |
| IOI (Vals) | 4.33% | #44 of 55 | Official leaderboard | |
| Code Arena | 1,341 | #100 of 124 | Official leaderboard | |
| Vibe Code Bench v1 | 3.09% | #14 of 17 | Official leaderboard | |
| ALE-Bench | 341 | #109 of 121 | Epoch AI | |
| Vibe Code Bench | 3.09% | #107 of 115 | Official leaderboard | |
| SWE-Bench Pro | 9.67% | #23 of 24 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 72.4% | #4 of 65 | Official leaderboard | |
| SnakeBench | 25 | #72 of 183 | Official leaderboard | |
| MCP-Universe | 26% | #15 of 30 | Official leaderboard | |
| Step Race | 2 | #31 of 59 | Official leaderboard | |
| VitaBench 2.0 | 35.9% | #12 of 20 | Official leaderboard | |
| tau2-bench | 75.9% | #44 of 69 | Model card | |
| Terminal-Bench | 24.5% | #13 of 18 | Epoch AI | |
| LisanBench | 157.0 | #98 of 133 | Official leaderboard | |
| Toolathlon | 18.8% | #39 of 50 | Official leaderboard | |
| BrowseComp | 45.1% | #62 of 77 | Model card | |
| Terminal-Bench 2.0 | 24.5% | #38 of 43 | Official leaderboard | |
| Elimination Game | 3 | #50 of 56 | Official leaderboard | |
| Agent Poker Bench | 946 | #16 of 17 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vals Finance Agent v1 | 27.1% | #27 of 47 | Official leaderboard | |
| LegalBench | 79.6% | #90 of 138 | Official leaderboard | |
| CorpFin v2 | 56.8% | #83 of 119 | Official leaderboard | |
| TaxEval v2 | 66.2% | #105 of 129 | Official leaderboard | |
| Vals Finance Agent | 36.5% | #42 of 49 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Spiral-Bench v1.2 | 30.8 | #15 of 21 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.