GLM-4.6 glm-4.6
zai-org · glm hybrid-reasoning flagship agentic
#14 overall #3 coding #3 agentic
- params
- 355B (A32B)
- arch
- moe
- context
- 198k
- license
- mit open weights
- released
- Sep 2025
- reasoning
- yes
- train compute
- 4.4e+24 FLOP
# why ranked
Overall: #14 — score 40.4 ● medium — one signal missing, weights renormalized
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.50 | 28.7 |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | 69.5 |
missing signals are dropped and the remaining weights renormalized — never imputed.
Coding: #3 — score 75.9 ● medium — one signal missing, weights renormalized
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.25 | 62.1 |
| aider_polyglot | 0.25 | — |
| arena_elo_code | 0.15 | — |
| swe_bench_verified | 0.35 | 85.7 |
missing signals are dropped and the remaining weights renormalized — never imputed.
Agentic: #3 — score 85.7 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| swe_bench_verified | 1.00 | 85.7 |
# trend
collecting history — trends appear after a few daily runs.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 45.8 | Artificial Analysis | — |
| AA Intelligence Index | 28.7 | Artificial Analysis | — |
| AA Math Index | 86.0 | Artificial Analysis | — |
| AIME 2025 | 0.9 / 1 | LLM Stats | — |
| Browsecomp | 0.5 / 1 | LLM Stats | — |
| SWE-bench Verified | 68.2 | SWE-bench | Sep 2025 |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| DeepInfra | fp4 | 198k | $0.43 | $1.74 | $0.76 | — | 99.9% |
| Venice | fp4 | 198k | $0.43 | $1.75 | $0.76 | — | 100.0% |
| Novita | bf16 | 200k | $0.55 | $2.20 | $0.96 | — | 97.1% |
| AtlasCloud | fp8 | 198k | $0.60 | $2.20 | $1.00 | — | 100.0% |
| Z.AI | fp4 | 198k | $0.60 | $2.20 | $1.00 | — | 61.1% |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
# variants
source aliases
- aa
glm-4.6- arena
GLM-4.6- openrouter
z-ai/glm-4.6