SpaceXAIGrok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is a SpaceXAI proprietary reasoning model, released 9 Mar 2026. Its best configuration ranks #152 of 785 on the BenchLeader Index at 58.5 ±2.0, in the upper half. The ± is the point: 222 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 human preference (66) and lowest in multimodal (59). At $1.56 per million tokens blended it is pricier than most ranked models. Output speed of 357 tokens per second puts it in the fastest quarter, with a first token in 8.0 s. Last measured 22 Oct 2026.
- Blended price
- $1.56/M
- $1.25 in · $2.50 out
- Output speed
- 357 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 8.00 s
- Context
- 2M
- Full answer
- –
- Cost per run
- –
- Released
- 9 Mar 2026
- Overall index59
- Reasoning65
- Coding65
- Maths63
- Human preference66
- Multimodal59
How its index has moved
19 Sept 2026 to 21 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 | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1484#59 | Arena (LMArena) |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1508#61 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Searchnot in index | 1206#15 | Arena (LMArena) |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1455#69 | Arena (LMArena) |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1444#74 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1471#47 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1447#43 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1474#52 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1458#75 | Arena (LMArena) |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Vision | 1259#57 | Arena (LMArena) |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| SpaceXAI | 384 tok/s | 19 s | $1.25 | $2.50 | 2M | – |
| SpaceXAI | 354 tok/s | 25 s | $1.25 | $2.50 | 2M | – |
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 at $0.200 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0013 | $0.0009 | 8.8 s |
| Summarize a 30-page report | 12,000 / 600 | $0.017 | $0.0071 | 9.7 s |
| Code edit | 6,000 / 1,500 | $0.011 | $0.0065 | 12.2 s |
| Agentic coding session | 60,000 / 4,000 | $0.085 | $0.038 | 19.2 s |
| Structured extraction | 2,000 / 200 | $0.0030 | $0.0014 | 8.6 s |
See also
Questions people ask
- What are Grok 4.20 Multi-Agent's benchmark scores?
- As of 24 Oct 2026, Grok 4.20 Multi-Agent scores 58.5 ±2.0 on the BenchLeader Index, strongest in human preference (66) and weakest in multimodal (59). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does Grok 4.20 Multi-Agent rank?
- Grok 4.20 Multi-Agent is #152 of 785 ranked configurations on 24 Oct 2026. 222 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 Grok 4.20 Multi-Agent cost per 1M tokens?
- As of 24 Oct 2026, Grok 4.20 Multi-Agent costs $1.25 per 1M input tokens and $2.50 per 1M output tokens, $1.56 blended (three input tokens per output token).
- When was Grok 4.20 Multi-Agent released?
- SpaceXAI released Grok 4.20 Multi-Agent on 9 Mar 2026.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Grok 4.20 Multi-Agent: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/grok-4-20-multi-agent.