# Multi-agent cooperation sustainability simulation on GOVSIM default experiment

Source: [Multi-agent cooperation sustainability simulation on GOVSIM default experiment](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment>)

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

Data updated: 2026-02-26T06:05:46.635Z

Evaluation of multi-agent cooperation and sustainability performance within the GOVSIM simulation environment, measured by metrics including Survival Rate, Efficiency, and Equality.

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 | Multi-agent cooperation sustainability simulation |
| Dataset (including any stated split) | GOVSIM default experiment |
| Metric | Survival Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Survival Rate](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment.md?metric=Survival%20Rate>): Higher is better; unit: PERCENT.

- [Survival Time](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment.md?metric=Survival%20Time>): Higher is better; unit: TIME.

- [Gain](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment.md?metric=Gain>): Higher is better; unit: SCALAR.

- [Efficiency](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment.md?metric=Efficiency>): Higher is better; unit: PERCENT.

- [Equality](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment.md?metric=Equality>): Higher is better; unit: PERCENT.

- [Over-usage](<https://www.sota2.com/research/sota/multi-agent-cooperation-sustainability-simulation-on-govsim-default-experiment.md?metric=Over-usage>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Survival Rate | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 53.3 | Not recorded | 68fa76161e209131cea6b551 |
| Claude-3 Opus | 46.7 | Not recorded | 68fa76161e209131cea6b551 |
| GPT-4-turbo | 40 | Not recorded | 68fa76161e209131cea6b551 |
| Qwen-110B | 20 | Not recorded | 68fa76161e209131cea6b551 |
| GPT-4 | 6.7 | Not recorded | 68fa76161e209131cea6b551 |
| Llama-3-8B | 0 | Not recorded | 68fa76161e209131cea6b551 |
| Llama-3-70B | 0 | Not recorded | 68fa76161e209131cea6b551 |
| Mistral-7B | 0 | Not recorded | 68fa76161e209131cea6b551 |
| Mixtral-8x7B | 0 | Not recorded | 68fa76161e209131cea6b551 |
| Qwen-72B | 0 | Not recorded | 68fa76161e209131cea6b551 |
| Claude-3 Haiku | 0 | Not recorded | 68fa76161e209131cea6b551 |
| Claude-3 Sonnet | 0 | Not recorded | 68fa76161e209131cea6b551 |
| GPT-3.5 | 0 | Not recorded | 68fa76161e209131cea6b551 |

### GPT-4o

Survival Rate: 53.3. Result ID: 6994251b3a6c3148491b5dc2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

### Claude-3 Opus

Survival Rate: 46.7. Result ID: 6994251b3a6c3148491b5dbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

### GPT-4-turbo

Survival Rate: 40. Result ID: 6994251b3a6c3148491b5dc1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

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

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

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

### Qwen-110B

Survival Rate: 20. Result ID: 6994251b3a6c3148491b5dbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Open-Weights"}. This record does not assert independent reproduction.

### GPT-4

Survival Rate: 6.7. Result ID: 6994251b3a6c3148491b5dc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

### Llama-3-8B

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5db6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Open-Weights"}. This record does not assert independent reproduction.

### Llama-3-70B

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5db7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Open-Weights"}. This record does not assert independent reproduction.

### Mistral-7B

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5db8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Open-Weights"}. This record does not assert independent reproduction.

### Mixtral-8x7B

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5db9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Open-Weights"}. This record does not assert independent reproduction.

### Qwen-72B

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5dba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Open-Weights"}. This record does not assert independent reproduction.

### Claude-3 Haiku

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5dbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

### Claude-3 Sonnet

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5dbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

### GPT-3.5

Survival Rate: 0. Result ID: 6994251b3a6c3148491b5dbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76161e209131cea6b551.md>)

[Implementation](<https://github.com/giorgiopiatti/GovSim>)

Recorded evaluation configuration: {"Weight Access":"Closed-Weights"}. This record does not assert independent reproduction.

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