Benchmark Almanac

BuildArena

GPT-5 45.3% leads since October 2025
Not in model cards
Version 1.0

Agents design machines in the Besiege simulator from written requirements. The simulator tests whether a vehicle reaches its target, how much weight a bridge supports, and how a lifting machine performs.

Westlake University ranks nine models on transport, support, and lift. The leaderboard reports a separate success rate for each task category.

Released
October 2025
Kind
Video games
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Agentic
Environment
Besiege
Run by
Anyone
In views
Agents, Robotics
Strongest model tested
GPT-5 #71 on the capability index
Last model added
August 2025
Scores refreshed
November 20th, 2026
9
Entries on its own leaderboard, 6 models we track

GPT-5 leads with 45.3% among models released by August 2025 GPT-5 leads with 45.3% among models released by August 2025

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-5 45.3%
  2. 2 Grok 4 18.1%
  3. 3 Doubao-Seed-1.6 9.20%
  4. 4 gpt-4o (snapshot unspecified) 7.77%
  5. 5 Claude Sonnet 4 6.60%
  6. 6 kimi-k2-turbo-preview 6.43%
  7. 7 DeepSeek-V3.1 4.83%
  8. 8 qwen-plus (Qwen3 series) 4.13%
  9. 9 Gemini 2.0 Flash Feb 2025 3.13%

Source: Official BuildArena leaderboard

#EntryScoreSettingDateSource
1 GPT-5 45.3% Baseline agentic workflow Aug 2025 Official leaderboard
2 Grok 4 18.1% Baseline agentic workflow Jul 2025 Official leaderboard
3 Doubao-Seed-1.6 9.20% Baseline agentic workflow Jun 2025 Official leaderboard
4 gpt-4o (snapshot unspecified) 7.77% Baseline agentic workflow Official leaderboard
5 Claude Sonnet 4 6.60% Baseline agentic workflow May 2025 Official leaderboard
6 kimi-k2-turbo-preview 6.43% Baseline agentic workflow Official leaderboard
7 DeepSeek-V3.1 4.83% Baseline agentic workflow Aug 2025 Official leaderboard
8 qwen-plus (Qwen3 series) 4.13% Baseline agentic workflow Official leaderboard
9 Gemini 2.0 Flash Feb 2025 3.13% Baseline agentic workflow Feb 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5 45.3% Baseline agentic workflow Aug 2025 Official leaderboard
2 Grok 4 18.1% Baseline agentic workflow Jul 2025 Official leaderboard
3 Doubao-Seed-1.6 9.20% Baseline agentic workflow Jun 2025 Official leaderboard
4 Claude Sonnet 4 6.60% Baseline agentic workflow May 2025 Official leaderboard
5 DeepSeek-V3.1 4.83% Baseline agentic workflow Aug 2025 Official leaderboard
6 Gemini 2.0 Flash Feb 2025 3.13% Baseline agentic workflow Feb 2025 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Transport, Support and Lift. Each ranks models on one part of the test. GPT-5 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Transport

6 models we track have a score here.

  1. 1 GPT-5 42.7%
  2. 2 Claude Sonnet 4 ↑2 12.5%
  3. 3 Grok 4 ↓1 11.5%
  4. 4 Doubao-Seed-1.6 ↓1 6.20%
  5. 5 DeepSeek-V3.1 2.60%
  6. 6 Gemini 2.0 Flash Feb 2025 1.60%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Oct 2025
GPT-5 45.3%

Source: Official BuildArena leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 Grok 4 Doubao-Seed-1.6 Gemini 2.0 Flash 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-5 Grok 4

Source: Official BuildArena leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

More in Games and long tasks

All 261 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%

Data audit

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (9 entries).
  • Pass Models scored 6 models we track, plus 3 other entries on its leaderboard.
  • Note Newest score The newest came 15 months ago, in August 2025, for DeepSeek-V3.1. That’s expected for a test replaced by BuildArena 2.0 Construction Challenge.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5 (#71).
  • Pass Headroom The best is 45.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on build-arena.github.io: 6 rows for models we track and 3 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check