# Wide Baseline Matching on ReasonMatch-Bench Indoor (test)

Source: [Wide Baseline Matching on ReasonMatch-Bench Indoor (test)](<https://www.sota2.com/research/sota/wide-baseline-matching-on-reasonmatch-bench-indoor-test>)

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

Data updated: 2026-06-04T09:40:50.510Z

Evaluation of Wide Baseline Matching performance on the test split of the ReasonMatch-Bench Indoor dataset, measured by L1, L2, and L3 metrics.

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 | Wide Baseline Matching |
| Dataset (including any stated split) | ReasonMatch-Bench Indoor (test) |
| Metric | L1 Error |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [L1 Error](<https://www.sota2.com/research/sota/wide-baseline-matching-on-reasonmatch-bench-indoor-test.md?metric=L1%20Error>): Lower is better; unit: SCALAR.

- [L2 Error](<https://www.sota2.com/research/sota/wide-baseline-matching-on-reasonmatch-bench-indoor-test.md?metric=L2%20Error>): Lower is better; unit: SCALAR.

- [L3 Error](<https://www.sota2.com/research/sota/wide-baseline-matching-on-reasonmatch-bench-indoor-test.md?metric=L3%20Error>): Lower is better; unit: SCALAR.

## Recorded results

| Method | L1 Error | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-VL-8B-Instruct | 25.5 | Not recorded | 6a2106a5c10484bac23f02fc |
| Claude-4.1-Opus | 31 | Not recorded | 6a2106a5c10484bac23f02fc |
| GPT-4o-241106 | 31.9 | Not recorded | 6a2106a5c10484bac23f02fc |
| Claude-4-Sonnet | 33 | Not recorded | 6a2106a5c10484bac23f02fc |
| Claude-4.5-Sonnet | 40.9 | Not recorded | 6a2106a5c10484bac23f02fc |
| Gemini-2.5-Pro | 48.3 | Not recorded | 6a2106a5c10484bac23f02fc |
| Qwen3-VL-235B | 52 | Not recorded | 6a2106a5c10484bac23f02fc |
| GPT-5-Chat | 52.4 | Not recorded | 6a2106a5c10484bac23f02fc |
| GPT-5-mini | 68.2 | Not recorded | 6a2106a5c10484bac23f02fc |
| Qwen3-VL-8B + DCRL | 84.6 | Not recorded | 6a2106a5c10484bac23f02fc |

### Qwen3-VL-8B-Instruct

L1 Error: 25.5. Result ID: 6a214814fbc373592c1d47db.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Parameters":"8B","Mode":"Instruct"}. This record does not assert independent reproduction.

### Claude-4.1-Opus

L1 Error: 31. Result ID: 6a214814fbc373592c1d47d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### GPT-4o-241106

L1 Error: 31.9. Result ID: 6a214814fbc373592c1d47d5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### Claude-4-Sonnet

L1 Error: 33. Result ID: 6a214814fbc373592c1d47d9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### Claude-4.5-Sonnet

L1 Error: 40.9. Result ID: 6a214814fbc373592c1d47d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### Gemini-2.5-Pro

L1 Error: 48.3. Result ID: 6a214814fbc373592c1d47d6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### Qwen3-VL-235B

L1 Error: 52. Result ID: 6a214814fbc373592c1d47da.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Parameters":"235B"}. This record does not assert independent reproduction.

### GPT-5-Chat

L1 Error: 52.4. Result ID: 6a214814fbc373592c1d47d4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### GPT-5-mini

L1 Error: 68.2. Result ID: 6a214814fbc373592c1d47d3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

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

### Qwen3-VL-8B + DCRL

L1 Error: 84.6. Result ID: 6a214814fbc373592c1d47dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106a5c10484bac23f02fc.md>)

[Implementation](<https://github.com/aim-uofa/ReasonMatch>)

Recorded evaluation configuration: {"Backbone":"Qwen3-VL-8B","Method":"DCRL"}. This record does not assert independent reproduction.

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