Multiverse Computing
availableShows if the model has enough results for an index.Quasar 438B
Quasar 438B is a reasoning model from Multiverse Computing in the Quasar family. 11 benchmarks count toward its score, in 4 categories.
IndexOverall score. 50 is the middle.55.5 ±7.9
CoverageShare of the index weight with results.70%
SpeedOutput tokens per second.146/s
Input / 1MUS dollars per 1M input tokens.$0.6
Output / 1MUS dollars per 1M output tokens.$1.8
ContextMaximum tokens in one request.1M
EloLMArena rating and rank.N/A
50 is the middle of the board. The range shows the doubt in the index.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
11 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Artificial Analysis Long Context Reasoning | Reasoning | 76.3% | 61.0 | — | — | Artificial Analysis |
| Artificial Analysis GPQA Diamond | Knowledge | 73.2% | 43.6 | — | — | Artificial Analysis |
| Terminal-Bench 2.1 (provider run) | Agentic | 69.3% | 65.0 | — | — | DeepSeek-AI |
| Terminal-Bench 2.1 (provider run) | Agentic | 69.3% | 65.0 | — | — | DeepSeek-AI |
| Artificial Analysis Coding Index | Coding | 61.2% | 62.1 | — | — | Artificial Analysis |
| Artificial Analysis SciCode | Coding | 48.1% | 59.6 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 33.1% | 61.0 | — | — | Artificial Analysis |
| Artificial Analysis Agentic Index | Agentic | 32.7% | 63.8 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 26.7% | 55.8 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 18.7% | 44.8 | — | — | Artificial Analysis |
| Artificial Analysis Omniscience Accuracy | Knowledge | 15.5% | 33.0 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 9.4% | 58.1 | — | — | Artificial Analysis |
11 benchmarks count, from 12 of 12 results. A grey row does not count. Too few models took that benchmark.