evals
Run evals on Jetty
Receipts

Every run

One row per game. Jetty runs link to their trajectory (inputs, agent log, artifacts); each has the exact runtime configuration that produced it.

GameStageWestEastWinnerGame minWall minModel costJetty trajectorySnapshot · patchFiles
ladder-gpt56terra-normal-g2cpu-ladder OpenRA AI (Normal)GPT-5.6 TerraOpenRA AI (Normal) 14.017.2$0.87 244c97eeopenra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-normal-g1cpu-ladder GPT-5.6 TerraOpenRA AI (Normal)OpenRA AI (Normal) 10.412.7$0.57 11382375openra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-medium-g2cpu-ladder OpenRA AI (Medium)GPT-5.6 TerraOpenRA AI (Medium) 5.88.1$0.30 25bbbda1openra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-medium-g1cpu-ladder GPT-5.6 TerraOpenRA AI (Medium)OpenRA AI (Medium) 10.814.6$0.64 cb9f4fa0openra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-easy-g2cpu-ladder OpenRA AI (Easy)GPT-5.6 TerraOpenRA AI (Easy) 16.124.3$0.95 59c1de0eopenra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-easy-g1cpu-ladder GPT-5.6 TerraOpenRA AI (Easy)OpenRA AI (Easy) 20.026.9$1.28 8799ebb9openra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-beginner-g2cpu-ladder OpenRA AI (Beginner)GPT-5.6 TerraOpenRA AI (Beginner) 20.027.5$1.18 30e5721dopenra-arena · 131dfe4fb60d603a config · result
ladder-gpt56terra-beginner-g1cpu-ladder GPT-5.6 TerraOpenRA AI (Beginner)OpenRA AI (Beginner) 20.022.8$1.21 76ee5949openra-arena · 131dfe4fb60d603a config · result
rr-sonnet5-gpt56terra-g3round-robin Claude Sonnet 5GPT-5.6 TerraGPT-5.6 Terra 5.38.2$0.53 8d343c33openra-arena · 131dfe4fb60d603a config · result
rr-sonnet5-gpt56terra-g2round-robin GPT-5.6 TerraClaude Sonnet 5Claude Sonnet 5 16.822.4$2.32 fc358032openra-arena · 131dfe4fb60d603a config · result
rr-jev-sonnet5-g4round-robin Claude Sonnet 5Jev RouterClaude Sonnet 5 13.220.8$1.00 542bd7d9openra-arena · 131dfe4fb60d603a config · result
rr-jev-sonnet5-g2round-robin Claude Sonnet 5Jev RouterJev Router 5.09.1$0.32 563b10caopenra-arena · 131dfe4fb60d603a config · result
rr-sonnet5-gpt56terra-g4round-robin GPT-5.6 TerraClaude Sonnet 5GPT-5.6 Terra 9.213.7$1.05 b35404b4openra-arena · 131dfe4fb60d603a config · result
rr-sonnet5-gpt56terra-g1round-robin Claude Sonnet 5GPT-5.6 TerraGPT-5.6 Terra 7.812.2$0.85 0bde81b2openra-arena · 131dfe4fb60d603a config · result
rr-jev-gpt56terra-g4round-robin GPT-5.6 TerraJev RouterGPT-5.6 Terra 7.111.6$0.56 6bafdc73openra-arena · 131dfe4fb60d603a config · result
rr-jev-gpt56terra-g3round-robin Jev RouterGPT-5.6 TerraGPT-5.6 Terra 5.27.8$0.36 8197bf3aopenra-arena · 131dfe4fb60d603a config · result
rr-jev-gpt56terra-g1round-robin Jev RouterGPT-5.6 TerraGPT-5.6 Terra 5.78.1$0.39 84bd0579openra-arena · 131dfe4fb60d603a config · result
rr-jev-gpt56terra-g2round-robin GPT-5.6 TerraJev RouterJev Router 6.08.9$0.39 3bb0113copenra-arena · 131dfe4fb60d603a config · result
rr-jev-sonnet5-g3round-robin Jev RouterClaude Sonnet 5Jev Router 5.67.7$0.34 54daab2eopenra-arena · 131dfe4fb60d603a config · result
rr-jev-sonnet5-g1round-robin Jev RouterClaude Sonnet 5Jev Router 4.97.8$0.27 ccd61be6openra-arena · 131dfe4fb60d603a config · result
cup1-final-g3pilot Jev RouterClaude Sonnet 5Jev Router 14.025.6$0.85 local– · – config · result
cup1-final-g2pilot Claude Sonnet 5Jev RouterJev Router 12.418.9$0.61 local– · – config · result
cup1-third-g2pilot GPT-5.6 TerraGemini 3.8 FlashGPT-5.6 Terra 5.96.2$0.46 local– · – config · result
cup1-third-g1pilot Gemini 3.8 FlashGPT-5.6 TerraGPT-5.6 Terra 4.55.1$0.35 local– · – config · result
cup1-final-g1pilot Jev RouterClaude Sonnet 5Claude Sonnet 5 7.312.1$0.37 local– · – config · result
cup1-sf1-g3pilot Jev RouterGPT-5.6 TerraJev Router 8.814.2$0.49 local– · – config · result
cup1-sf1-g2pilot GPT-5.6 TerraJev RouterJev Router 14.028.1$0.84 local– · – config · result
cup1-sf2-g2pilot Gemini 3.8 FlashClaude Sonnet 5Claude Sonnet 5 7.79.3$0.60 local– · – config · result
cup1-sf2-g1pilot Claude Sonnet 5Gemini 3.8 FlashClaude Sonnet 5 5.26.2$0.38 local– · – config · result
cup1-sf1-g1pilot Jev RouterGPT-5.6 TerraGPT-5.6 Terra 8.815.0$0.53 local– · – config · result

Want this kind of eval for your own agents?

Every run on this site is a Jetty runbook: versioned instructions, a pinned sandbox, and a trajectory you can inspect. Point Jetty at your task and get the same receipts.