BenchLeader

Grok 4.20 Multi-Agent

Quality#59 of 339
58.5Index
Top quarter
+8.3 on the median
Price#163 of 255
$1.56per 1M tokens
Dearer than most
1.8× the median
Speed#3 of 216
316tokens/s
Top 10%
4.0× the median
Value#159 of 255
37.4points per $
Below the median
0.7× the median

Better value: Claude Haiku 5.5 scores 56.7 for $0.200/M, 87% cheaper.

7 cheaper ranked models score higher: Gemini 3.7 Flash (62.1, $1.50), Gemini 3.6 Flash (61.0, $1.50), Gemini 3.8 Flash (60.2, $1.50) and 4 more.

As of 15 Nov 2026, Grok 4.20 Multi-Agent by SpaceXAI scores 58.5 on the BenchLeader Index (608 ranked configurations), with its best results in human preference (66) and weakest in multimodal (59). API pricing: $1.25 per 1M input tokens and $2.50 per 1M output tokens ($1.56 blended at 3:1), list price on 15 Nov 2026. It streams about 320 tokens/s (OpenRouter). Released 9 Mar 2026.

Key facts (as of 15 Nov 2026)

  • Grok 4.20 Multi-Agent API pricing: $1.25 per 1M input tokens and $2.50 per 1M output tokens ($1.56 blended at 3:1) (list price, 15 Nov 2026).
  • Grok 4.20 Multi-Agent streams about 320 tokens/s (OpenRouter, 15 Nov 2026).
  • Grok 4.20 Multi-Agent was released on 9 Mar 2026 (SpaceXAI).

In detail. Grok 4.20 Multi-Agent is a SpaceXAI proprietary reasoning model, released 9 Mar 2026. Its best configuration ranks #128 of 608 on the BenchLeader Index at 58.5 ±2.0, in the upper half. The ± is the point: 221 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 316 tokens per second puts it in the fastest quarter, with a first token in 16.7 s. Last measured 11 Nov 2026.

Blended price
$1.56/M
$1.25 in · $2.50 out
via OpenRouter
Output speed
316 tok/s
OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
First answer
17 s
Context
2M
via OpenRouter
Cost per task
–
Tokens per task
–
Released
9 Mar 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index59
  2. Reasoning65
  3. Coding64
  4. Maths63
  5. Human preference66
  6. Multimodal59

Embed this rank

More badge styles
[![Grok 4.20 Multi-Agent on BenchLeader: #59 overall](https://www.benchleader.com/badge/grok-4-20-multi-agent.svg?style=compact)](https://www.benchleader.com/models/grok-4-20-multi-agent)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when SpaceXAI ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

How its index has moved

19 Sep 2026 to 15 Nov 2026
565961

The 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

Benchmarknot statedSourceTrend
Arena Hard Prompts1484#61Arena (LMArena)
Arena Expertnot in index1483#71Arena (LMArena)

Coding

Benchmarknot statedSourceTrend
Arena Coding1509#63Arena (LMArena)

Agents & tools

Benchmarknot statedSourceTrend
Arena Searchnot in index1207#15Arena (LMArena)

Maths

Benchmarknot statedSourceTrend
Arena Maths1455#72Arena (LMArena)

Instruction following

Benchmarknot statedSourceTrend
Arena Instruction Followingnot in index1444#77Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1471#50Arena (LMArena)
Arena Creative Writingnot in index1448#46Arena (LMArena)
Arena Multi-turnnot in index1475#54Arena (LMArena)
Arena Longer Queriesnot in index1458#79Arena (LMArena)

Multimodal

Benchmarknot statedSourceTrend
Arena Vision1259#57Arena (LMArena)

API pricing: 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.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
SpaceXAI493 tok/s2.67 s$1.25$2.502M–

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.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0013$0.000917.7 s
Summarize a 30-page report12,000 / 600$0.017$0.007118.6 s
Code edit6,000 / 1,500$0.011$0.006521.5 s
Agentic coding session60,000 / 4,000$0.085$0.03829.4 s
Structured extraction2,000 / 200$0.0030$0.001417.3 s

More from SpaceXAI

New this month

Compare Grok 4.20 Multi-Agent with…

See also

Embed or cite

Show where Grok 4.20 Multi-Agent ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![Grok 4.20 Multi-Agent on BenchLeader: #59 overall](https://www.benchleader.com/badge/grok-4-20-multi-agent.svg)](https://www.benchleader.com/models/grok-4-20-multi-agent)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 15). Grok 4.20 Multi-Agent on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 15, 2026, from https://www.benchleader.com/models/grok-4-20-multi-agent

BibTeX:

@misc{benchleader_grok_4_20_multi_agent_20261115,
  author       = {{BenchLeader}},
  title        = {{Grok 4.20 Multi-Agent on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/grok-4-20-multi-agent}},
  note         = {Data as of 2026-11-15}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Grok 4.20 Multi-Agent's benchmark scores?
As of 15 Nov 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 independent benchmark results only, and every score on this page links to its publisher.
How does Grok 4.20 Multi-Agent rank?
Grok 4.20 Multi-Agent is #128 of 608 ranked configurations on 15 Nov 2026. 221 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
How much does Grok 4.20 Multi-Agent cost per 1M tokens?
As of 15 Nov 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).
Is Grok 4.20 Multi-Agent better than Qwen3.8 Max?
As of 15 Nov 2026, Grok 4.20 Multi-Agent and Qwen3.8 Max (max) are neck and neck on quality (58.5 vs 58.7 on the BenchLeader Index, inside the ±3.9 margin of error), and Grok 4.20 Multi-Agent costs 1.9× less, which makes it the better buy for most workloads. The head-to-head page has the benchmark-by-benchmark detail.
When was Grok 4.20 Multi-Agent released?
SpaceXAI released Grok 4.20 Multi-Agent on 9 Mar 2026.

Data as of 15 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Grok 4.20 Multi-Agent: benchmarks, pricing, speed and rank”, data as of 15 Nov 2026, https://www.benchleader.com/models/grok-4-20-multi-agent.