JFinBench - Tools - Terminus-2 Harbor 0.24.0: leaderboard
Same321examplesandGPT5.1grading, mean3runs; terminal/webtools; fixednamedharness; highestnativeeffort. Allcompleted/failedattemptsperAppendixD, notbest-ofharnessselection. PreserveDS1017checkpoint; noSPRO/reasoningdefaults inferred. Metric: Overall score (%). Source: https://arxiv.org/html/2611.18130v1
Metric: Overall score (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 97.3 | #8 |
| 2 | Claude Fable 5 | 96.4 | #28 |
| 3 | Gemini 3.8 Flash | 94.2 | #39 |
| 4 | Kimi K3.1 Pro | 92.1 | #32 |
| 5 | DeepSeek V4.1 Flash (1017) | 88.6 | #44 |
| 6 | GLM-5.3 Flash | 87.6 | #136 |
| 7 | Kimi K3 | 86.1 | #59 |
| 8 | MiMo-V2.6-Pro | 85.3 | #86 |
| 9 | Qwen 3.8 Flash | 83.3 | #128 |
| 10 | MiMo-V2.6-Flash | 73.2 | #176 |
| 11 | Kimi K2.6 | 70.4 | #191 |
| 12 | Mistral Large 4 | 70.1 | #143 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=jfinbench-tools-terminus-2-harbor-0-24-0 · How It Works · Data refreshed daily, snapshot 2026-11-17.