Multiverse ComputingQuasar 438B
Quasar 438B is a Multiverse Computing proprietary reasoning model, released 10 Aug 2026. Its best configuration (max reasoning effort) ranks #222 of 785 on the BenchLeader Index at 55.8 ±2.1, in the upper half. The ± is the point: 258 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (63) and lowest in reasoning (56). At $0.165 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 185 tokens per second puts it in the fastest quarter, with a first answer in 12.0 s. Last measured 10 Aug 2026.
- Blended price
- $0.165/M
- $0.110 in · $0.330 out
- Output speed
- 185 tok/s
- measured by Artificial Analysis
- First answer
- 12 s
- Context
- 1M
- Full answer
- 15 s
- median, reasoning included
- Cost per run
- –
- Released
- 10 Aug 2026
- Overall index56
- Reasoning56
- Agents & tools57
- Knowledge60
- Long context63
- Composite59
How its index has moved
8 Oct 2026 to 23 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. 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 | max | Source | Trend |
|---|---|---|---|
| GPQA Diamond (AA)not in index | 73.2%#272 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 18.7%#227 | Artificial Analysis | |
| CritPt | 9.4%#124 | Artificial Analysis |
Coding
| Benchmark | max | Source | Trend |
|---|---|---|---|
| SciCode (AA)not in index | 48.1%#126 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 1.0%#128 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 69.3%#76 | Artificial Analysis |
Agents & tools
| Benchmark | max | Source | Trend |
|---|---|---|---|
| GDPval-AA v2.1not in index | 34.1%#72 | Artificial Analysis | |
| τ³-Banking (AA) | 28.7%#72 | Artificial Analysis | |
| AutomationBenchnot in index | 23.9%#128 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 5.4%#159 | Artificial Analysis |
Knowledge
| Benchmark | max | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -2.6#149 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 15.5%#411 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 78.6%#13 | Artificial Analysis |
Long context
| Benchmark | max | Source | Trend |
|---|---|---|---|
| AA-LCR | 76.3%#145 | Artificial Analysis | |
| MLCRnot in index | 9.4%#119 | Artificial Analysis |
Composite
| Benchmark | max | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 26.7#148 | Artificial Analysis |
Price history
The price above, per 1M tokens, every day it changed.
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 | $0.0001 | – | 13.6 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0015 | – | 15.2 s |
| Code edit | 6,000 / 1,500 | $0.0012 | – | 20.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.0079 | – | 33.6 s |
| Structured extraction | 2,000 / 200 | $0.0003 | – | 13.1 s |
More from Multiverse Computing
See also
Questions people ask
- What are Quasar 438B's benchmark scores?
- As of 24 Oct 2026, Quasar 438B (max effort) scores 55.8 ±2.1 on the BenchLeader Index, strongest in long context (63) and weakest in reasoning (56). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does Quasar 438B rank?
- Quasar 438B (max effort) is #222 of 785 ranked configurations on 24 Oct 2026. 258 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Quasar 438B cost per 1M tokens?
- As of 24 Oct 2026, Quasar 438B costs $0.110 per 1M input tokens and $0.330 per 1M output tokens, $0.165 blended (three input tokens per output token). The list price last changed on 23 Oct 2026.
- When was Quasar 438B released?
- Multiverse Computing released Quasar 438B on 10 Aug 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Quasar 438B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/quasar-438b.