# Context-faithful Reasoning on ConFiQA MC

Source: [Context-faithful Reasoning on ConFiQA MC](<https://www.sota2.com/research/sota/context-faithful-reasoning-on-confiqa-mc>)

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

Data updated: 2026-02-26T05:57:38.177Z

Evaluation of model performance on the ConFiQA MC dataset for Context-faithful Reasoning, measured by Pc, Po, MR, and EM.

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 | Context-faithful Reasoning |
| Dataset (including any stated split) | ConFiQA MC |
| Metric | Pc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Pc](<https://www.sota2.com/research/sota/context-faithful-reasoning-on-confiqa-mc.md?metric=Pc>): Higher is better; unit: PERCENT.

- [Po](<https://www.sota2.com/research/sota/context-faithful-reasoning-on-confiqa-mc.md?metric=Po>): Higher is better; unit: PERCENT.

- [MR](<https://www.sota2.com/research/sota/context-faithful-reasoning-on-confiqa-mc.md?metric=MR>): Higher is better; unit: PERCENT.

- [EM](<https://www.sota2.com/research/sota/context-faithful-reasoning-on-confiqa-mc.md?metric=EM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pc | Result date | Report paper |
| --- | --- | --- | --- |
| LLAMA2-7B | 38.8 | Not recorded | 68fa764c1e209131cea6c3c3 |
| LLAMA2-13B | 35.3 | Not recorded | 68fa764c1e209131cea6c3c3 |
| LLAMA3-8B | 21.7 | Not recorded | 68fa764c1e209131cea6c3c3 |
| GEMINI-1.5-PRO | 21.1 | Not recorded | 68fa764c1e209131cea6c3c3 |
| MISTRAL-7B | 14.1 | Not recorded | 68fa764c1e209131cea6c3c3 |
| QWEN2-7B | 10 | Not recorded | 68fa764c1e209131cea6c3c3 |
| CHATGPT-4 | 8.7 | Not recorded | 68fa764c1e209131cea6c3c3 |
| CHATGPT-4o | 1.6 | Not recorded | 68fa764c1e209131cea6c3c3 |

### LLAMA2-7B

Pc: 38.8. Result ID: 699437613a6c3148491bd23d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Model Version":"chat"}. This record does not assert independent reproduction.

### LLAMA2-13B

Pc: 35.3. Result ID: 699437613a6c3148491bd23e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Model Version":"chat"}. This record does not assert independent reproduction.

### LLAMA3-8B

Pc: 21.7. Result ID: 699437613a6c3148491bd23f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

Recorded evaluation configuration: {"Model Version":"instruct"}. This record does not assert independent reproduction.

### GEMINI-1.5-PRO

Pc: 21.1. Result ID: 699437613a6c3148491bd243.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MISTRAL-7B

Pc: 14.1. Result ID: 699437613a6c3148491bd240.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

Recorded evaluation configuration: {"Model Version":"instruct-v0.2"}. This record does not assert independent reproduction.

### QWEN2-7B

Pc: 10. Result ID: 699437613a6c3148491bd241.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

Recorded evaluation configuration: {"Model Version":"instruct"}. This record does not assert independent reproduction.

### CHATGPT-4

Pc: 8.7. Result ID: 699437613a6c3148491bd242.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CHATGPT-4o

Pc: 1.6. Result ID: 699437613a6c3148491bd244.

[Reporting paper](<https://www.sota2.com/research/paper/68fa764c1e209131cea6c3c3.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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