BlogLLM Benchmark Scores as Published, Side by Side
BankerToolBench: Results as Published
Every result the catalog holds for BankerToolBench: 11 models from 7 developers, read from 3 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Tool Use and WorkflowsMaintainer BankerToolBench authorsIntroduced 2026Data version 2026103001, as of 2026-10-30
BankerToolBench scores an agent on banking and financial-services workflows that call tools and documents; answers are graded against dataset rubrics by a judge model. The score is the rubric pass rate.
Not checked against a maintainer's page.
BankerToolBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.6 SolOpenAI, released 2026-07-09 | 74.6% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 70.04% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 76.2% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | - |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 81.34% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 67.03% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| DeepSeek-V4.1-FlashDeepSeek, released 2026-09-10 | 73.7% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | - |
| Kimi K3Moonshot AI, released 2026-07-16 | 69.1% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | - |
| GLM-5.3Z.ai, released 2026-08-18 | 74.5% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | - |
| MiniMax-M3.1-FlashMiniMax, released 2026-10-19 | 76.2% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25; printed on 1 more page | Harness: OpenCode 1.17.18 |
| MiniMax M3MiniMax, released 2026-06-01 | 76.12% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| MiniMax M2.7MiniMax, released 2026-03-18 | 63.89% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.