# General Reasoning on BBH (Cost and Token Consumption)

Source: [General Reasoning on BBH (Cost and Token Consumption)](<https://www.sota2.com/research/sota/general-reasoning-on-bbh-cost-and-token-consumption>)

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

Data updated: 2026-04-08T07:06:56.894Z

Evaluation of model performance on the General Reasoning tasks within the Big-Bench Hard (BBH) suite, specifically reporting resource utilization metrics like Relative Cost and Token Consumption.

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 | General Reasoning |
| Dataset (including any stated split) | BBH |
| Metric | Relative Cost |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 14 of 14 |
| 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

- [Relative Cost](<https://www.sota2.com/research/sota/general-reasoning-on-bbh-cost-and-token-consumption.md?metric=Relative%20Cost>): Lower is better; unit: SCALAR.

- [Token Consumption](<https://www.sota2.com/research/sota/general-reasoning-on-bbh-cost-and-token-consumption.md?metric=Token%20Consumption>): Lower is better; unit: SIZE.

## Recorded results

| Method | Relative Cost | Result date | Report paper |
| --- | --- | --- | --- |
| CoT | 1 | Not recorded | 69d5e0de7d0172140ec758ba |
| Analogical Prompting | 1.04 | Not recorded | 69d5e0de7d0172140ec758ba |
| TDA-RC | 1.1 | Not recorded | 69d5e0de7d0172140ec758ba |
| Role / Persona Prompting | 1.12 | Not recorded | 69d5e0de7d0172140ec758ba |
| Prompt Canvas | 1.12 | Not recorded | 69d5e0de7d0172140ec758ba |
| Instruction Induction | 1.15 | Not recorded | 69d5e0de7d0172140ec758ba |
| HoT | 1.23 | Not recorded | 69d5e0de7d0172140ec758ba |
| Self-Refine | 2.28 | Not recorded | 69d5e0de7d0172140ec758ba |
| AoT | 3.33 | Not recorded | 69d5e0de7d0172140ec758ba |
| AFlow | 4.16 | Not recorded | 69d5e0de7d0172140ec758ba |
| CoT-SC | 5.21 | Not recorded | 69d5e0de7d0172140ec758ba |
| ToT | 5.61 | Not recorded | 69d5e0de7d0172140ec758ba |
| GoT | 6.08 | Not recorded | 69d5e0de7d0172140ec758ba |
| FoT | 8.18 | Not recorded | 69d5e0de7d0172140ec758ba |

### CoT

Relative Cost: 1. Result ID: 69d5fdef47f34ce924be0ca2.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

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

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

### Analogical Prompting

Relative Cost: 1.04. Result ID: 69d5fdef47f34ce924be0cae.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

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

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

### TDA-RC

Relative Cost: 1.1. Result ID: 69d5fdef47f34ce924be0caf.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

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

### Role / Persona Prompting

Relative Cost: 1.12. Result ID: 69d5fdef47f34ce924be0cac.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75251e209131cea66219.md>)

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

### Prompt Canvas

Relative Cost: 1.12. Result ID: 69d5fdef47f34ce924be0cad.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76141e209131cea6b49b.md>)

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

### Instruction Induction

Relative Cost: 1.15. Result ID: 69d5fdef47f34ce924be0cab.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c981e209131cea34bad.md>)

[Implementation](<https://github.com/orhonovich/instruction-induction>)

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

### HoT

Relative Cost: 1.23. Result ID: 69d5fdef47f34ce924be0caa.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b831e209131cea88d06.md>)

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

### Self-Refine

Relative Cost: 2.28. Result ID: 69d5fdef47f34ce924be0ca4.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fc4.md>)

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

### AoT

Relative Cost: 3.33. Result ID: 69d5fdef47f34ce924be0ca9.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77991e209131cea74466.md>)

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

### AFlow

Relative Cost: 4.16. Result ID: 69d5fdef47f34ce924be0ca5.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78111e209131cea769ef.md>)

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

### CoT-SC

Relative Cost: 5.21. Result ID: 69d5fdef47f34ce924be0ca3.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

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

Recorded evaluation configuration: {"Evaluation Model":"GPT-4o-mini","n":"5"}. This record does not assert independent reproduction.

### ToT

Relative Cost: 5.61. Result ID: 69d5fdef47f34ce924be0ca6.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea50930.md>)

[Implementation](<https://github.com/princeton-nlp/tree-of-thought-llm>)

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

### GoT

Relative Cost: 6.08. Result ID: 69d5fdef47f34ce924be0ca7.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ba1e209131cea582e3.md>)

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

### FoT

Relative Cost: 8.18. Result ID: 69d5fdef47f34ce924be0ca8.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e0de7d0172140ec758ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b01e209131cea74c26.md>)

Recorded evaluation configuration: {"Evaluation Model":"GPT-4o-mini","n":"8"}. This record does not assert independent reproduction.

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