phoenix-inst-chat-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1232 ± 32, rank #9400 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLMsPark - Prisoner's Dilemma (Single Play) | 1236.5 | Elo rating (initial 1000, K=32) | 100 |
| LLMsPark - Trust Game (Multiple Play) | 973.4 | Elo rating (initial 1000, K=32) | 69.2 |
| LLMsPark - Nim Game | 965.1 | Elo rating (initial 1000, K=32) | 61.5 |
| LLMsPark - Dictator Game (Single Play) | 988.85 | Elo rating (initial 1000, K=32) | 38.5 |
| LLMsPark - Trust Game (Single Play) | 910.56 | Elo rating (initial 1000, K=32) | 38.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.08 | MC2 (%) (0-shot) | 36.4 |
| Open LLM Leaderboard v1 - MMLU | 39.06 | Accuracy (%) (5-shot) | 20.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 44.71 | Normalized accuracy (%) (25-shot) | 20.3 |
| Open LLM Leaderboard v1 - HellaSwag | 63.23 | Normalized accuracy (%) (10-shot) | 16.4 |
| Open LLM Leaderboard v1 - GSM8K | 1.29 | Accuracy (%) (5-shot) | 16.3 |
| Open LLM Leaderboard v1 - WinoGrande | 62.83 | Accuracy (%) (5-shot) | 15.7 |
| LLMsPark - Dictator Game (Multiple Play) | 952.67 | Elo rating (initial 1000, K=32) | 15.4 |
Interactive version: theaggregate.ai/model?slug=phoenix-inst-chat-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.