Quasar 438B (max, based on GLM-5.2)
Not yet ranked: too few independent results so far. Released 10 Aug 2026.
- Blended price
- $0.900/M
- $0.600 in · $1.80 out
- Output speed
- 177 tok/s
- First answer
- 12 s
- Context
- 1M
- Knowledge63
- Long context65
- Composite63
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 73.2%#262 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 18.7%#170 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode (AA)not in index | 48.1%#79 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -2.6#106 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 76.3%#100 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 27.1#100 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0008 | – | 13.9 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0083 | – | 15.6 s |
| Code edit | 6,000 / 1,500 | $0.0063 | – | 20.7 s |
| Agentic coding session | 60,000 / 4,000 | $0.043 | – | 34.8 s |
| Structured extraction | 2,000 / 200 | $0.0016 | – | 13.3 s |
See also
Data as of 9 Sept 2026. Compare with another model.