Run Your Own LLM Evaluation
Test any models with your prompts. Start free, no credit card required.
Coding Performance with 10 Evaluators — Run
Comprehensive evaluation of 3 language models across 1 system prompt with rigorous benchmarking and scoring criteria.
7.94
claude-fable-5
5.00
Spread: 6.47 pts
2262ms
Response time
120
12 total responses
Executive Insights
Key takeaways from this evaluation
Top Performer
claude-fable-5
7.94
2.35 pts ahead of #2
Model Rankings
Ranked by overall performance score
claude-fable-5
anthropic/claude-fable-5
Good
Responses
4
Avg Latency
3117ms
Cost
$0.1057
claude-opus-4.8
anthropic/claude-opus-4.8
Average
Responses
4
Avg Latency
1406ms
Cost
$0.0403
gpt-5.5
openai/gpt-5.5
Needs Improvement
Responses
4
Avg Latency
—
Cost
$0.0308
Evaluator Consensus
How 9 evaluator models ranked the candidates via blind comparison
majority Agreement
8 of 9 evaluators agree on the top model
claude-fable-5
Avg Rank
1.1
Range
#1–2
#1 Votes
8/9
Latency
3117ms
claude-opus-4.8
Avg Rank
2.0
Range
#1–3
#1 Votes
1/9
Latency
1406ms
gpt-5.5
Avg Rank
2.9
Range
#2–3
#1 Votes
0/9
Latency
—
gpt-5.4-mini
gemini-3.1-flash-lite-preview
claude-sonnet-4.6
minimax-m2.7
kimi-k2.5
deepseek-v3.2
mistral-small-2603
qwen3.5-27b
nova-2-lite-v1
Score Comparison
Visual comparison of all model scores
Performance by System Prompt
How each model performs across different evaluation contexts
Top Performer
claude-fable-5
7.94
Performance by Test Prompt
Model results broken down by individual test prompts
| Test Prompt | Avg Score |
|---|---|
Javascript Function 3 responses | 5.00 |
Write an Interval Merge Function 3 responses | 5.00 |
Debug Python 3 responses | 5.00 |
Refactor Javascript 3 responses | 5.00 |
About This Evaluation
Methodology, criteria weights, and evaluation confidence
12
Total Responses
120
Total Evaluations
