# Science Question Answering on ARC-C (Accuracy, TFLOPs)

Source: [Science Question Answering on ARC-C (Accuracy, TFLOPs)](<https://www.sota2.com/research/sota/science-question-answering-on-arc-c-accuracy-tflops>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-12T08:21:32.346Z

Evaluation of model performance on the ARC-C dataset for Science Question Answering, reporting Accuracy and computational cost (TFLOPs).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Science Question Answering |
| Dataset (including any stated split) | ARC-C |
| Metric | Accuracy (ARC-C) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy (ARC-C)](<https://www.sota2.com/research/sota/science-question-answering-on-arc-c-accuracy-tflops.md?metric=Accuracy%20(ARC-C)>): Higher is better; unit: PERCENT.

- [TFLOPs](<https://www.sota2.com/research/sota/science-question-answering-on-arc-c-accuracy-tflops.md?metric=TFLOPs>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy (ARC-C) | Result date | Report paper |
| --- | --- | --- | --- |
| Ours-context-unaware | 93.6 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| Ours-context-unaware | 91.38 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| Ours-context-unaware | 88.99 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| Ours-context-unaware | 88.48 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| Ours-context-unaware | 88.48 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| Ours-context-unaware | 86.86 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| T2T-context-unaware | 23.74 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| T2T-context-unaware | 23.39 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| T2T-context-unaware | 22.96 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| T2T-context-unaware | 22.87 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| C2C-context-unaware | 22.52 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| T2T-context-unaware | 20.61 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| T2T-context-unaware | 19.48 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| C2C-context-unaware | 10.7 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| C2C-context-unaware | 10.35 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| C2C-context-unaware | 7.39 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| C2C-context-unaware | 4.96 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |
| C2C-context-unaware | 2.78 | Not recorded | 6a2b92d3d33dfb23e783b2d9 |

### Ours-context-unaware

Accuracy (ARC-C): 93.6. Result ID: 6a2bc177fbc373592c2a2eed.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"8B → 4B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### Ours-context-unaware

Accuracy (ARC-C): 91.38. Result ID: 6a2bc177fbc373592c2a2ee7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"4B → 8B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### Ours-context-unaware

Accuracy (ARC-C): 88.99. Result ID: 6a2bc177fbc373592c2a2ef6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"14B → 8B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### Ours-context-unaware

Accuracy (ARC-C): 88.48. Result ID: 6a2bc177fbc373592c2a2ef0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"8B → 14B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### Ours-context-unaware

Accuracy (ARC-C): 88.48. Result ID: 6a2bc177fbc373592c2a2ef3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"14B → 4B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### Ours-context-unaware

Accuracy (ARC-C): 86.86. Result ID: 6a2bc177fbc373592c2a2eea.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"4B → 14B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### T2T-context-unaware

Accuracy (ARC-C): 23.74. Result ID: 6a2bc177fbc373592c2a2eeb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"8B → 4B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### T2T-context-unaware

Accuracy (ARC-C): 23.39. Result ID: 6a2bc177fbc373592c2a2ee8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"4B → 14B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### T2T-context-unaware

Accuracy (ARC-C): 22.96. Result ID: 6a2bc177fbc373592c2a2eee.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"8B → 14B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### T2T-context-unaware

Accuracy (ARC-C): 22.87. Result ID: 6a2bc177fbc373592c2a2ef4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"14B → 8B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### C2C-context-unaware

Accuracy (ARC-C): 22.52. Result ID: 6a2bc177fbc373592c2a2ee6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be91e209131cea8b3ff.md>)

[Implementation](<https://github.com/thu-nics/C2C>)

Recorded evaluation configuration: {"Pair":"4B → 8B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### T2T-context-unaware

Accuracy (ARC-C): 20.61. Result ID: 6a2bc177fbc373592c2a2ef1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"14B → 4B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### T2T-context-unaware

Accuracy (ARC-C): 19.48. Result ID: 6a2bc177fbc373592c2a2ee5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

Recorded evaluation configuration: {"Pair":"4B → 8B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### C2C-context-unaware

Accuracy (ARC-C): 10.7. Result ID: 6a2bc177fbc373592c2a2ee9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be91e209131cea8b3ff.md>)

[Implementation](<https://github.com/thu-nics/C2C>)

Recorded evaluation configuration: {"Pair":"4B → 14B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### C2C-context-unaware

Accuracy (ARC-C): 10.35. Result ID: 6a2bc177fbc373592c2a2eec.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be91e209131cea8b3ff.md>)

[Implementation](<https://github.com/thu-nics/C2C>)

Recorded evaluation configuration: {"Pair":"8B → 4B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### C2C-context-unaware

Accuracy (ARC-C): 7.39. Result ID: 6a2bc177fbc373592c2a2eef.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be91e209131cea8b3ff.md>)

[Implementation](<https://github.com/thu-nics/C2C>)

Recorded evaluation configuration: {"Pair":"8B → 14B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### C2C-context-unaware

Accuracy (ARC-C): 4.96. Result ID: 6a2bc177fbc373592c2a2ef2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be91e209131cea8b3ff.md>)

[Implementation](<https://github.com/thu-nics/C2C>)

Recorded evaluation configuration: {"Pair":"14B → 4B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

### C2C-context-unaware

Accuracy (ARC-C): 2.78. Result ID: 6a2bc177fbc373592c2a2ef5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92d3d33dfb23e783b2d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be91e209131cea8b3ff.md>)

[Implementation](<https://github.com/thu-nics/C2C>)

Recorded evaluation configuration: {"Pair":"14B → 8B","Context Setting":"context-unaware"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
