Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-5.2 (Medium)
OpenAI
- Quasar 438B (Max, Based on GLM-5.2)
Multiverse Computing
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-5.2 (Medium) OpenAI | Quasar 438B (Max, Based on GLM-5.2) Multiverse Computing | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 26.5 | Best: 26.7 | |
| Coding | — | 61.2 | |
| Math | 96.7 | — | |
| Agentic | — | 31.4 | |
| Speed | — | 145 t/s | |
| TTFT | — | 1.3 s | |
| Input · $ / 1M tokens | $1.75×2.9 relative to the lowest price among the compared models | Best: $0.60 | |
| Output · $ / 1M tokens | $14×7.8 relative to the lowest price among the compared models | Best: $1.80 | |
| Context window | 400K | Best: 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | — | $2.02 |
Intelligence
- GPT-5.2 (Medium)
- 26.5
- Quasar 438B (Max, Based on GLM-5.2)
- Best: 26.7
Coding
- GPT-5.2 (Medium)
- —
- Quasar 438B (Max, Based on GLM-5.2)
- 61.2
Math
- GPT-5.2 (Medium)
- 96.7
- Quasar 438B (Max, Based on GLM-5.2)
- —
Agentic
- GPT-5.2 (Medium)
- —
- Quasar 438B (Max, Based on GLM-5.2)
- 31.4
Speed
- GPT-5.2 (Medium)
- —
- Quasar 438B (Max, Based on GLM-5.2)
- 145 t/s
TTFT
- GPT-5.2 (Medium)
- —
- Quasar 438B (Max, Based on GLM-5.2)
- 1.3 s
Input · $ / 1M tokens
- GPT-5.2 (Medium)
- $1.75×2.9 relative to the lowest price among the compared models
- Quasar 438B (Max, Based on GLM-5.2)
- Best: $0.60
Output · $ / 1M tokens
- GPT-5.2 (Medium)
- $14×7.8 relative to the lowest price among the compared models
- Quasar 438B (Max, Based on GLM-5.2)
- Best: $1.80
Context window
- GPT-5.2 (Medium)
- 400K
- Quasar 438B (Max, Based on GLM-5.2)
- Best: 1M
Reasoning
- GPT-5.2 (Medium)
- Yes
- Quasar 438B (Max, Based on GLM-5.2)
- Yes
Open weights
- GPT-5.2 (Medium)
- No
- Quasar 438B (Max, Based on GLM-5.2)
- No
Cost / task
- GPT-5.2 (Medium)
- —
- Quasar 438B (Max, Based on GLM-5.2)
- $2.02
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- GPT-5.2 (Medium)26.5 · $4.81
- Quasar 438B (Max, Based on GLM-5.2)26.7 · $0.90