# Tool Learning under Instruction with Missing Key Information on NoisyToolBench IMKI 1.0 (test)

Source: [Tool Learning under Instruction with Missing Key Information on NoisyToolBench IMKI 1.0 (test)](<https://www.sota2.com/research/sota/tool-learning-under-instruction-with-missing-key-information-on-noisytoolbench-imki-1-0-test>)

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

Data updated: 2026-04-30T06:42:20.903Z

Evaluation of model performance on tool learning capabilities when key instructional information is missing, using the test split of NoisyToolBench IMKI version 1.0. Results are reported using A1, A2, and A3 success rate 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 | Tool Learning under Instruction with Missing Key Information |
| Dataset (including any stated split) | NoisyToolBench IMKI 1.0 (test) |
| Metric | A1 Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 32 of 32 |
| 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

- [A1 Success Rate](<https://www.sota2.com/research/sota/tool-learning-under-instruction-with-missing-key-information-on-noisytoolbench-imki-1-0-test.md?metric=A1%20Success%20Rate>): Higher is better; unit: PERCENT.

- [A2 Success Rate](<https://www.sota2.com/research/sota/tool-learning-under-instruction-with-missing-key-information-on-noisytoolbench-imki-1-0-test.md?metric=A2%20Success%20Rate>): Higher is better; unit: PERCENT.

- [A3 Success Rate](<https://www.sota2.com/research/sota/tool-learning-under-instruction-with-missing-key-information-on-noisytoolbench-imki-1-0-test.md?metric=A3%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | A1 Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| CoT + AwN | 94 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 90 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 88 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 88 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 86 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 86 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 82 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 82 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 80 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 80 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 80 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 78 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 74 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 74 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 74 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 72 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 70 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 64 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 62 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 58 | Not recorded | 68fa77061e209131cea7092e |
| CoT + AwN | 54 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 52 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT + AwN | 52 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 44 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 42 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 26 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 24 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 22 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 10 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 2 | Not recorded | 68fa77061e209131cea7092e |
| CoT | 0 | Not recorded | 68fa77061e209131cea7092e |
| DFSDT | 0 | Not recorded | 68fa77061e209131cea7092e |

### CoT + AwN

A1 Success Rate: 94. Result ID: 69f2f91c47f34ce924d8bce3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gpt-4"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 90. Result ID: 69f2f91c47f34ce924d8bce7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gpt-4o"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 88. Result ID: 69f2f91c47f34ce924d8bce1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gpt-3.5"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 88. Result ID: 69f2f91c47f34ce924d8bce9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gpt-4o"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 86. Result ID: 69f2f91c47f34ce924d8bcef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gemini-1.5"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 86. Result ID: 69f2f91c47f34ce924d8bcfd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"DeepSeek-R1"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 82. Result ID: 69f2f91c47f34ce924d8bce4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"gpt-4"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 82. Result ID: 69f2f91c47f34ce924d8bcf1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gemini-1.5"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 80. Result ID: 69f2f91c47f34ce924d8bce5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gpt-4"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 80. Result ID: 69f2f91c47f34ce924d8bcf9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"O3-mini"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 80. Result ID: 69f2f91c47f34ce924d8bcfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"DeepSeek-R1"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 78. Result ID: 69f2f91c47f34ce924d8bcf7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"O3-mini"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 74. Result ID: 69f2f91c47f34ce924d8bcde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"gpt-3.5"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 74. Result ID: 69f2f91c47f34ce924d8bcdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"gpt-3.5"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 74. Result ID: 69f2f91c47f34ce924d8bce2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"gpt-4"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 72. Result ID: 69f2f91c47f34ce924d8bced.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"deepseek-v3"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 70. Result ID: 69f2f91c47f34ce924d8bceb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"deepseek-v3"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 64. Result ID: 69f2f91c47f34ce924d8bce0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"gpt-3.5"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 62. Result ID: 69f2f91c47f34ce924d8bcf0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"gemini-1.5"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 58. Result ID: 69f2f91c47f34ce924d8bce8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"gpt-4o"}. This record does not assert independent reproduction.

### CoT + AwN

A1 Success Rate: 54. Result ID: 69f2f91c47f34ce924d8bcf3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"claude-3.5"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 52. Result ID: 69f2f91c47f34ce924d8bce6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"gpt-4o"}. This record does not assert independent reproduction.

### DFSDT + AwN

A1 Success Rate: 52. Result ID: 69f2f91c47f34ce924d8bcf5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

Recorded evaluation configuration: {"Model":"claude-3.5"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 44. Result ID: 69f2f91c47f34ce924d8bcea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"deepseek-v3"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 42. Result ID: 69f2f91c47f34ce924d8bcec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"deepseek-v3"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 26. Result ID: 69f2f91c47f34ce924d8bcf4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"claude-3.5"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 24. Result ID: 69f2f91c47f34ce924d8bcf2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"claude-3.5"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 22. Result ID: 69f2f91c47f34ce924d8bcee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"gemini-1.5"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 10. Result ID: 69f2f91c47f34ce924d8bcfa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"DeepSeek-R1"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 2. Result ID: 69f2f91c47f34ce924d8bcfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"DeepSeek-R1"}. This record does not assert independent reproduction.

### CoT

A1 Success Rate: 0. Result ID: 69f2f91c47f34ce924d8bcf6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Model":"O3-mini"}. This record does not assert independent reproduction.

### DFSDT

A1 Success Rate: 0. Result ID: 69f2f91c47f34ce924d8bcf8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77061e209131cea7092e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ce1e209131cea4d478.md>)

[Implementation](<https://github.com/OpenBMB/ToolBench>)

Recorded evaluation configuration: {"Model":"O3-mini"}. This record does not assert independent reproduction.

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