Leaderboard
Rankings are built from human pairwise votes. In each battle, two models respond to the same prompt — voters choose which response better embodies the target value.
Bradley-Terry Elo computed from human pairwise votes.
Updated every 5 min · live from votes
How warmly each model responds to human-centered prompts.
| Model | Win Rate | BT Elo |
|---|---|---|
1anthropic/claude-3-5-haiku | 100% | 1829 |
2Qwen 2.5 72B | 100% | 1203 |
3Claude 3.5 Haiku | 75% | 1078 |
4Llama 3.3 70B | 33% | 966 |
5GPT-4o Mini | 40% | 862 |
6Mistral Small 3.1 | 0% | 300 |
7Gemini 2.0 Flash | 0% | 300 |
Preference for stability, institutions, and incremental change.
| Model | Win Rate | BT Elo |
|---|---|---|
1Llama 3.3 70B | 100% | 1658 |
2Qwen 2.5 72B | 100% | 1658 |
3Gemini 2.0 Flash | 25% | 855 |
4GPT-4o Mini | 33% | 300 |
5Claude 3.5 Haiku | 50% | 300 |
Alignment with ecological stewardship and planet-first values.
Not enough votes yet — keep judging to unlock rankings.
Commitment to sustained relationships and group solidarity.
| Model | Win Rate | BT Elo |
|---|---|---|
1Gemini 2.0 Flash | 100% | 1765 |
2Qwen 2.5 72B | 100% | 1205 |
3Claude 3.5 Haiku | 100% | 1205 |
4Llama 3.3 70B | 50% | 971 |
5Mistral Small 3.1 | 0% | 300 |
How each model ranks across all four value dimensions. Darker = higher ranked.
| Model | Kindness | Conservatism | Deep Ecology | Loyalty | Avg Rank |
|---|---|---|---|---|---|
| Qwen 2.5 72B | #2 1203 | #2 1658 | — | #2 1205 | 2.0 |
| Llama 3.3 70B | #4 966 | #1 1658 | — | #4 971 | 3.0 |
| Claude 3.5 Haiku | #3 1078 | #5 300 | — | #3 1205 | 3.7 |
| Gemini 2.0 Flash | #7 300 | #3 855 | — | #1 1765 | 3.7 |
| GPT-4o Mini | #5 862 | #4 300 | — | — | 4.5 |
| Mistral Small 3.1 | #6 300 | — | — | #5 300 | 5.5 |
Win rate of the row model vs each column opponent. Ties are split 50/50. Darker = higher win rate.
Row wins vs column
| 4oMi | Haik | Gmni | Llma | Mist | Qwen | |
|---|---|---|---|---|---|---|
| GPT-4o Mini | — | 0% 3v | — | 100% 1v | 100% 1v | — |
| Claude 3.5 Haiku | 100% 3v | — | — | 0% 1v | — | — |
| Gemini 2.0 Flash | — | — | — | — | — | 0% 1v |
| Llama 3.3 70B | 0% 1v | 100% 1v | — | — | — | — |
| Mistral Small 3.1 | 0% 1v | — | — | — | — | — |
| Qwen 2.5 72B | — | — | 100% 1v | — | — | — |
Row wins vs column
| 4oMi | Haik | Gmni | Llma | Mist | Qwen | |
|---|---|---|---|---|---|---|
| GPT-4o Mini | — | 50% 2v | 0% 1v | — | — | — |
| Claude 3.5 Haiku | 50% 2v | — | — | — | — | — |
| Gemini 2.0 Flash | 100% 1v | — | — | 0% 2v | — | 0% 1v |
| Llama 3.3 70B | — | — | 100% 2v | — | — | — |
| Mistral Small 3.1 | — | — | — | — | — | — |
| Qwen 2.5 72B | — | — | 100% 1v | — | — | — |
Row wins vs column
| 4oMi | Haik | Gmni | Llma | Mist | Qwen | |
|---|---|---|---|---|---|---|
| GPT-4o Mini | — | — | — | — | — | — |
| Claude 3.5 Haiku | — | — | — | — | — | — |
| Gemini 2.0 Flash | — | — | — | — | — | — |
| Llama 3.3 70B | — | — | — | — | — | — |
| Mistral Small 3.1 | — | — | — | — | — | — |
| Qwen 2.5 72B | — | — | — | — | — | — |
Row wins vs column
| 4oMi | Haik | Gmni | Llma | Mist | Qwen | |
|---|---|---|---|---|---|---|
| GPT-4o Mini | — | — | — | — | — | — |
| Claude 3.5 Haiku | — | — | — | — | 100% 1v | — |
| Gemini 2.0 Flash | — | — | — | 100% 1v | — | — |
| Llama 3.3 70B | — | — | 0% 1v | — | 100% 1v | — |
| Mistral Small 3.1 | — | 0% 1v | — | 0% 1v | — | 0% 1v |
| Qwen 2.5 72B | — | — | — | — | 100% 1v | — |
Contribute
Head to the battle page, read two model responses side by side, and pick which one better reflects the target value. Every vote updates the leaderboard.
