BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

Time Horizon Index: KSP leaderboard

As of 6 Nov 2026, the top score on Time Horizon Index: KSP is 91.3% by Claude Opus 5.5 (Anthropic), ahead of GPT-6 Astra at 90.5%, across 13 model configurations with a published result (Vals AI, result dated 7 Oct 2026). The agent must plan and fly missions in Kerbal Space Program, a long-horizon task with physics and many steps. Time Horizon Index: KSP is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Claude Opus 5.5 holds the top Time Horizon Index: KSP score at 91.3% (Vals AI, 7 Oct 2026).
  • GPT-6 Astra is second on Time Horizon Index: KSP at 90.5% (Vals AI, 7 Oct 2026).
  • Time Horizon Index: KSP: Running a Kerbal Space Program mission end to end. Run by Vals AI (Vals AI).
  • 13 model configurations have a published Time Horizon Index: KSP result on BenchLeader (BenchLeader, 6 Nov 2026).
  • Time Horizon Index: KSP does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Running a Kerbal Space Program mission end to end. Run by Vals AI.

Published by
Vals AI
Category
Agents & tools
Index weight
Reference only
Models
13
Data as of
6 Nov 2026

Vals AI (vals.ai).

What the test looks like

The agent must plan and fly missions in Kerbal Space Program, a long-horizon task with physics and many steps.

How it is scored

Mission progress score, run by Vals AI.

What to keep in mind

A single, unusual environment; read as a long-horizon signal only.

Top 15
  1. 1Claude Opus 5.591.3%
  2. 2GPT-6 Astra (max)90.5%
  3. 3Claude Fable 5.163.3%
  4. 4Gemini 4 Argon (high)52.5%
  5. 5GPT-5.6 Sol (max)23.8%
  6. 6Claude Opus 518.8%
  7. 7Gemini 3.8 Flash (high)18.8%
  8. 8Claude Opus 4.811.8%
  9. 9Kimi K3 (max)10.5%
  10. 10GPT-5.5 (xhigh)8.3%
  11. 11Grok 4.5 (high)6.3%
  12. 12Grok 4.6 (high)5.8%
  13. 13Muse Spark 1.1 (xhigh)1.7%
13 of 13
#
1Claude Opus 5.591.3%63.4$1303.372026-10-07
2GPT-6 Astramax90.5%67.8$4206.592026-10-07
3Claude Fable 5.163.3%66.4$4655.012026-10-07
4Gemini 4 Argonhigh52.5%66.0$708.632026-10-07
5GPT-5.6 Solmax23.8%65.4$2027.202026-10-07
6Claude Opus 518.8%65.2$1348.772026-10-07
7Gemini 3.8 Flashhigh18.8%62.0$543.142026-10-07
8Claude Opus 4.811.8%60.0$1499.322026-10-07
9Kimi K3max10.5%62.1$216.432026-10-07
10GPT-5.5xhigh8.3%64.3$516.362026-10-07
11Grok 4.5high6.3%56.9$344.042026-10-07
12Grok 4.6high5.8%60.5$225.122026-10-07
13Muse Spark 1.1xhigh1.7%59.5$144.922026-10-07

More agents & tools benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on Time Horizon Index: KSP

Cite as: BenchLeader, “Time Horizon Index: KSP leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/vals_time_horizon_ksp.

Time Horizon Index: KSP: questions

What does Time Horizon Index: KSP measure?
The agent must plan and fly missions in Kerbal Space Program, a long-horizon task with physics and many steps. Scores are reported in percent of tasks solved; higher is better.
What is the top score on Time Horizon Index: KSP?
As of 6 Nov 2026, the highest score on Time Horizon Index: KSP is 91.3% by Claude Opus 5.5 (result dated 7 Oct 2026), ahead of GPT-6 Astra at 90.5%. Scores come from Vals AI and are re-read daily.
Which AI model leads Time Horizon Index: KSP?
Claude Opus 5.5 leads Time Horizon Index: KSP with 91.3% as of 6 Nov 2026 (result dated 7 Oct 2026), ahead of GPT-6 Astra at 90.5%.
How many models have Time Horizon Index: KSP results?
13 model configurations have a Time Horizon Index: KSP result on BenchLeader, all taken from Vals AI.
Who runs Time Horizon Index: KSP and how often is it updated?
Time Horizon Index: KSP is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Time Horizon Index: KSP count toward the BenchLeader Index?
No. Time Horizon Index: KSP is shown for reference but left out of the composite index.