Kaelum Bench v0.2 · Public Calibration
Compare verified benchmark evidence by configuration.
Each row is one authenticated model configuration. Scores remain provisional and link to the exact published run evidence. Missing suites are not treated as zero.
Signed public release
Configuration-specific results, without an overall score
Coverage states which of the five defined suites has published evidence. Results from different provider routes, runtimes, or material parameters remain separate.
- v0.2
- Updated
- 16 configurations · 37 runs
16 of 16 configurations
Scroll horizontally to compare suites.
| Model configuration | Provider route | Accounting Knowledge | HGB Reporting | IFRS Reporting | Financial Analysis | Accounting Capstone | Coverage |
|---|---|---|---|---|---|---|---|
| Kimi K3moonshotai/kimi-k3Max reasoning | openrouter/moonshotai/int4openrouter-tool-free-non-streaming-v6 | 91.7444%Model-judgedProvisional | 88.4333%DeterministicProvisional | 91.4444%DeterministicProvisional | 66.5000%DeterministicProvisional | Missing | 4 / 5 |
| NVIDIA Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55bHigh reasoning | openrouter/togetheropenrouter-tool-free-non-streaming-v6 | 85.0762%Model-judgedProvisional | 78.2508%DeterministicProvisional | 89.6667%DeterministicProvisional | 61.1701%DeterministicProvisional | Missing | 4 / 5 |
| Qwen3.6-35B-A3Bqwen/qwen3.6-35b-a3bMax supported reasoning | openrouter/akashml/fp8openrouter-tool-free-non-streaming-v6 | 93.2556%Model-judgedProvisional | 89.3619%DeterministicProvisional | 90.6667%DeterministicProvisional | 77.1222%DeterministicProvisional | Missing | 4 / 5 |
| Claude Sonnet 5 (Max)anthropic/claude-sonnet-5Max reasoning | openrouter/azureopenrouter-tool-free-non-streaming-v6 | Missing | 85.6000%DeterministicProvisional | 90.7778%DeterministicProvisional | 59.7368%DeterministicProvisional | Missing | 3 / 5 |
| DeepSeek V4 Flashdeepseek/deepseek-v4-flashXhigh reasoning | openrouter/alibabaopenrouter-tool-free-non-streaming-v6 | Missing | 84.5111%DeterministicProvisional | 90.5556%DeterministicProvisional | 52.1983%DeterministicProvisional | Missing | 3 / 5 |
| Gemini 3.5 Flashgoogle/gemini-3.5-flashHigh reasoning | openrouter/google-vertexopenrouter-tool-free-non-streaming-v6 | Missing | 92.3778%DeterministicProvisional | 91.8889%DeterministicProvisional | 77.7889%DeterministicProvisional | Missing | 3 / 5 |
| Grok 4.5x-ai/grok-4.5High reasoning | openrouter/xaiopenrouter-tool-free-non-streaming-v6 | Missing | 90.6667%DeterministicProvisional | 91.4444%DeterministicProvisional | 56.4111%DeterministicProvisional | Missing | 3 / 5 |
| Kimi K2.6moonshotai/kimi-k2.6Max supported reasoning | openrouter/modelrun/fp4openrouter-tool-free-non-streaming-v6 | 94.6556%Model-judgedProvisional | 90.1778%DeterministicProvisional | Missing | 87.5427%DeterministicProvisional | Missing | 3 / 5 |
| MiniMax M3minimax/minimax-m3Max supported reasoning | openrouter/morphopenrouter-tool-free-non-streaming-v6 | Missing | 89.2730%DeterministicProvisional | 88.5000%DeterministicProvisional | 91.9444%DeterministicProvisional | Missing | 3 / 5 |
| Claude Sonnet 5 (Max)anthropic/claude-sonnet-5Max reasoning | openrouter/azureopenrouter-tool-free-non-streaming-v6 | 93.1556%Model-judgedProvisional | Missing | Missing | Missing | Missing | 1 / 5 |
| DeepSeek V4 Flashdeepseek/deepseek-v4-flashXhigh reasoning | openrouter/alibabaopenrouter-tool-free-non-streaming-v6 | 94.9889%Model-judgedProvisional | Missing | Missing | Missing | Missing | 1 / 5 |
| Gemini 3.5 Flashgoogle/gemini-3.5-flashHigh reasoning | openrouter/google-vertexopenrouter-tool-free-non-streaming-v5 | 90.2667%Model-judgedProvisional | Missing | Missing | Missing | Missing | 1 / 5 |
| GLM 5.2z-ai/glm-5.2Xhigh reasoning | openrouter/waferopenrouter-tool-free-non-streaming-v6 | Missing | Missing | Missing | 67.7094%DeterministicProvisional | Missing | 1 / 5 |
| GLM 5.2z-ai/glm-5.2Xhigh reasoning | openrouter/waferopenrouter-tool-free-non-streaming-v4 | 96.0222%Model-judgedProvisional | Missing | Missing | Missing | Missing | 1 / 5 |
| Grok 4.5x-ai/grok-4.5High reasoning | openrouter/xaiopenrouter-tool-free-non-streaming-v4 | 95.9206%Model-judgedProvisional | Missing | Missing | Missing | Missing | 1 / 5 |
| MiniMax M3minimax/minimax-m3Max supported reasoning | openrouter/morphopenrouter-tool-free-non-streaming-v5 | 80.5444%Model-judgedProvisional | Missing | Missing | Missing | Missing | 1 / 5 |