chat benchmark
Multi-Challenge Leaderboard
Multi-Challenge is a multi-turn conversation evaluation benchmark for assessing LLMs across instruction retention, inference memory, reliable versioned editing, and self-coherence.
Updated Sep 5, 2026
Models29
Model coverage29
MetricScore
EvidenceC
Multi-Challenge Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova 2 ProAmazon | Score77.70% | Percentile100.00% | Participants29 | EvidenceC | Evaluated |
| Rank02 | ModelAMNova 2 LiteAmazon | Score76.60% | Percentile96.43% | Participants29 | EvidenceC | Evaluated |
| Rank03 | ModelAMNova 2 OmniAmazon | Score75.50% | Percentile92.86% | Participants29 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score69.60% | Percentile89.29% | Participants29 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score67.60% | Percentile85.71% | Participants29 | EvidenceC | Evaluated |
| Rank06 | ModelNV | Score63.80% | Percentile82.14% | Participants29 | EvidenceC | Evaluated |
| Rank07 | ModelST | Score62.60% | Percentile78.57% | Participants29 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score61.50% | Percentile75.00% | Participants29 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score60.80% | Percentile71.43% | Participants29 | EvidenceC | Evaluated |
| Rank10 | ModelOP | Score60.40% | Percentile67.86% | Participants29 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score60.00% | Percentile64.29% | Participants29 | EvidenceC | Evaluated |
| Rank12 | ModelNV | Score55.23% | Percentile60.71% | Participants29 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score54.50% | Percentile57.14% | Participants29 | EvidenceC | Evaluated |
| Rank14 | ModelMA | Score54.10% | Percentile53.57% | Participants29 | EvidenceC | Evaluated |
| Rank15 | ModelMA | Score54.10% | Percentile50.00% | Participants29 | EvidenceC | Evaluated |
| Rank16 | ModelMI | Score53.00% | Percentile46.43% | Participants29 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score49.00% | Percentile42.86% | Participants29 | EvidenceC | Evaluated |
| Rank18 | ModelMI | Score44.70% | Percentile39.29% | Participants29 | EvidenceC | Evaluated |
| Rank19 | ModelMI | Score44.70% | Percentile35.71% | Participants29 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score43.80% | Percentile32.14% | Participants29 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score43.00% | Percentile28.57% | Participants29 | EvidenceC | Evaluated |
| Rank22 | ModelOP | Score40.30% | Percentile25.00% | Participants29 | EvidenceC | Evaluated |
| Rank23 | ModelOP | Score39.90% | Percentile21.43% | Participants29 | EvidenceC | Evaluated |
| Rank24 | ModelNV | Score38.50% | Percentile17.86% | Participants29 | EvidenceC | Evaluated |
| Rank25 | ModelOP | Score38.30% | Percentile14.29% | Participants29 | EvidenceC | Evaluated |
| Rank26 | ModelOP | Score35.80% | Percentile10.71% | Participants29 | EvidenceC | Evaluated |
| Rank27 | ModelAC | Score33.70% | Percentile7.14% | Participants29 | EvidenceC | Evaluated |
| Rank28 | ModelAC | Score18.90% | Percentile3.57% | Participants29 | EvidenceC | Evaluated |
| Rank29 | ModelOP | Score15.00% | Percentile0.00% | Participants29 | EvidenceC | Evaluated |
Multi-Challenge Highlights
The leading models and scores on this benchmark.
Multi-Challenge Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Multi-Challenge
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Multi-Challenge?
What Multi-Challenge measures and how its scores work.
Multi-Challenge is a chat benchmark that evaluates models through sustained, contextually complex dialogues across topics including travel planning, technical documentation, and professional communication.
It measures instruction retention, inference memory, reliable versioned editing, and self-coherence using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of C.
- Family
- Multi-Challenge
- Modality
- text
- Primary category
- chat
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Multi-Challenge.
Which model scores highest on Multi-Challenge?
Nova 2 Pro is currently ranked first with 77.70%.
What are the top three models on Multi-Challenge?
The current leaders are Nova 2 Pro (77.70%), Nova 2 Lite (76.60%), and Nova 2 Omni (75.50%).
Which Multi-Challenge model has the lowest official input price?
GPT-4.1 nano has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among Multi-Challenge results?
The fastest matched records are GPT-4.1 mini (467.39 tok/s via OpenAI), GPT-4.1 nano (138.14 tok/s via OpenAI), and GPT-4o (132.00 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.