Evidence record
DeepSeek V4 Flash 0731
CharXiv · Evidence record
Original source charts and materials
CharXiv with images withheld
Original evaluator results · source order
Select systems
Attempted answer with image withheld
0–100%Tests understanding and reasoning over charts. Neo’s withheld-image adaptation measures attempts without the required input.
The original visual capability benchmark and the missing-image behavioral test measure different constructs. Report dates and original executor are shown with this assessment.
Evaluation conditions and system configurations
- DeepSeek V4 Flash 0731
- Withheld-image CharXiv questions; attempts include correct and incorrect guesses. · CharXiv with images withheld
- modelVersion: not specified · harness: not specified · tools: not specified · budget: not specified
| System / configuration | Attempted answer with image withheld | Publication / verification |
|---|---|---|
| 48.2% | Published2026-09-11 |
Assessment provenance
Evaluating Kimi K3 for Misalignment Risks → · External report
Actual evaluation: Neo Research · Model record →
Method and scope
Tests understanding and reasoning over charts. Neo’s withheld-image adaptation measures attempts without the required input.
- Evidence type
- Benchmark
- Assessment subject
- The model or agent in the stated task configuration.
- Primary dimension
- Capability
- Evidence snapshot
- 2026-10-29.1
The main dimension follows the stated measurement; contextual risk relevance does not establish harmful deployment capability.
Source finding
Source-reported measurements in §1.1.1; Figure 1. Transcription is not independent experimental replication.
Limitations
The original visual capability benchmark and the missing-image behavioral test measure different constructs.
The original visual capability benchmark and the missing-image behavioral test measure different constructs.
Related research questions
References
- [1] CharXiv
- [2] Evaluating Kimi K3 for Misalignment Risks. 2026-09-11. September 2026 ; §1.1.1; Figure 1