GLM-4.7 Flash glm-4.7-flash
zai-org · glm efficient
unranked — no quality signals yet
- params
- 31.2B
- arch
- dense
- context
- 198k
- license
- mit open weights
- released
- Jan 2026
- reasoning
- yes
- downloads/30d
- 2.7M
# why ranked
Overall: provisional — score 22.9 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.50 | 22.9 |
| arena_elo | 0.30 | — |
| bench_composite | 0.20 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
collecting history — trends appear after a few daily runs.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Intelligence Index | 22.9 | Artificial Analysis | — |
| AIME 2025 | 0.9 / 1 | LLM Stats | — |
| Browsecomp | 0.4 / 1 | LLM Stats | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M blend | tps | uptime |
|---|---|---|---|---|---|---|---|
| DeepInfra | bf16 | 198k | $0.06 | $0.40 | $0.15 | — | 100.0% |
| Cloudflare | unknown | 128k | $0.06 | $0.40 | $0.15 | — | 43.1% |
| Novita | bf16 | 200k | $0.07 | $0.40 | $0.15 | — | 94.6% |
| Venice | fp8 | 125k | $0.12 | $0.50 | $0.22 | — | 100.0% |
blended = (3·input + output) / 4 per 1M tokens · cheapest first
source aliases
- aa
glm-4.7-flash- openrouter
z-ai/glm-4.7-flash