CharXiv Reasoning (with tools)
Reasoning about paper figures and tables (with tools; Python, search and other tools differ by source).
- Category
- Multimodal
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 3total
- All model rankings (records) · Ranked results: 4
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
Show rankings including legacy and unavailable models (entries: 4)
official results (Kimi K3.1 Pro (Hugging Face model card, moonshotai))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Kimi K3.1 Pro | Max | 93.4% | — | Moonshot AI | Kimi K3.1 Pro (Hugging Face model card, moonshotai)Retrieved 2026-11-13 · Vendor-reported value (self-reported by Moonshot AI). Table column heading Kimi K3.1 Pro (max), table note: all Kimi K3.1 Pro results use reasoning effort max, temperature 1.0, top-p 0.95. With tools (Python); average of 4 runs.Source excerptCharXiv (RQ) w/ python | 93.4Location HF model card "3. Evaluation Results" table, CharXiv (RQ) w/ python row, Kimi K3.1 Pro (max) column (leftmost numeric column). Supporting footnote: Agentic 11 |
official results (Kimi K3 (Hugging Face model card, moonshotai))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Kimi K3 | Max | 91.3% | — | Moonshot AI | Kimi K3 (Hugging Face model card, moonshotai)Retrieved 2026-11-13 · Vendor-reported value (self-reported by Moonshot AI). Table note: All Kimi K3 results are obtained with reasoning effort set to 'max' and temperature = 1.0Source excerptCharXiv (RQ) | 84.8 / 91.3Location HF model card "3. Evaluation Results" table, CharXiv (RQ) (right-hand value in the without tools / with tools pair) row, Kimi K3 (max) column (leftmost numeric column). Supporting footnote: table note (vision tools use Python) |
official results (Gemini 3.7 Flash model card)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Gemini 3.6 Flash | not stated | 89.4% | — | Gemini 3.7 Flash model cardRetrieved 2026-11-13 · Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.com/models/evals-methodology/gemini-3-7-flash): All of the results are run with the Gemini API ... with default sampling settings unless indicated otherwise. Gemini computed in-house; tools are search and code executionSource excerptWith tools | 89.4%Location Gemini 3.7 Flash model card Evaluation table, CharXiv Reasoning(With tools) row, Gemini 3.6 Flash column. In-house computation basis: methodology PDF, Multimodal / CharXiv Reasoning | |
| 2 | Gemini 3.7 Flash | not stated | 88.7% | — | Gemini 3.7 Flash model cardRetrieved 2026-11-13 · Vendor-reported value. Table in the Google model card. methodology PDF (deepmind.com/models/evals-methodology/gemini-3-7-flash): All of the results are run with the Gemini API ... with default sampling settings unless indicated otherwise. Gemini computed in-house; tools are search and code executionSource excerptWith tools | 88.7%Location Gemini 3.7 Flash model card Evaluation table, CharXiv Reasoning(With tools) row, Gemini 3.7 Flash column. In-house computation basis: methodology PDF, Multimodal / CharXiv Reasoning |