reasoning benchmark
MCP Atlas Leaderboard
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
Updated Aug 17, 2026
Models33
Model coverage33
MetricScore
EvidenceB
MCP Atlas Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score88.1% | Percentile100.0% | Participants33 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score84.2% | Percentile96.9% | Participants33 | EvidenceC | Evaluated |
| Rank03 | ModelBY | Score83.8% | Percentile93.8% | Participants33 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score83.6% | Percentile90.6% | Participants33 | EvidenceC | Evaluated |
| Rank05 | ModelAN | Score82.2% | Percentile87.5% | Participants33 | EvidenceC | Evaluated |
| Rank06 | ModelBY | Score80.3% | Percentile84.4% | Participants33 | EvidenceC | Evaluated |
| Rank07 | ModelTM | Score79.6% | Percentile81.3% | Participants33 | EvidenceC | Evaluated |
| Rank08 | ModelTE | Score79.1% | Percentile78.1% | Participants33 | EvidenceC | Evaluated |
| Rank09 | ModelAN | Score77.3% | Percentile75.0% | Participants33 | EvidenceC | Evaluated |
| Rank10 | ModelZA | Score76.8% | Percentile71.9% | Participants33 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score76.4% | Percentile68.8% | Participants33 | EvidenceC | Evaluated |
| Rank12 | ModelMA | Score76.0% | Percentile65.6% | Participants33 | EvidenceC | Evaluated |
| Rank13 | ModelME | Score75.5% | Percentile62.5% | Participants33 | EvidenceC | Evaluated |
| Rank14 | ModelOP | Score75.3% | Percentile59.4% | Participants33 | EvidenceC | Evaluated |
| Rank15 | ModelMI | Score74.2% | Percentile56.3% | Participants33 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score74.1% | Percentile53.1% | Participants33 | EvidenceC | Evaluated |
| Rank17 | ModelDE | Score73.6% | Percentile50.0% | Participants33 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score73.2% | Percentile46.9% | Participants33 | EvidenceC | Evaluated |
| Rank19 | ModelZA | Score71.8% | Percentile43.8% | Participants33 | EvidenceC | Evaluated |
| Rank20 | ModelGO | Score69.2% | Percentile40.6% | Participants33 | EvidenceC | Evaluated |
| Rank21 | ModelDE | Score69.0% | Percentile37.5% | Participants33 | EvidenceC | Evaluated |
| Rank22 | ModelZA | Score67.8% | Percentile34.4% | Participants33 | EvidenceC | Evaluated |
| Rank23 | ModelDE | Score67.4% | Percentile31.3% | Participants33 | EvidenceC | Evaluated |
| Rank24 | ModelOP | Score67.2% | Percentile28.1% | Participants33 | EvidenceC | Evaluated |
| Rank25 | ModelAC | Score62.8% | Percentile25.0% | Participants33 | EvidenceC | Evaluated |
| Rank26 | ModelAN | Score62.7% | Percentile21.9% | Participants33 | EvidenceC | Evaluated |
| Rank27 | ModelAN | Score62.3% | Percentile18.8% | Participants33 | EvidenceC | Evaluated |
| Rank28 | ModelAN | Score61.3% | Percentile15.6% | Participants33 | EvidenceC | Evaluated |
| Rank29 | ModelOP | Score60.6% | Percentile12.5% | Participants33 | EvidenceC | Evaluated |
| Rank30 | ModelOP | Score57.7% | Percentile9.4% | Participants33 | EvidenceC | Evaluated |
| Rank31 | ModelGO | Score57.4% | Percentile6.3% | Participants33 | EvidenceC | Evaluated |
| Rank32 | ModelOP | Score56.1% | Percentile3.1% | Participants33 | EvidenceC | Evaluated |
| Rank33 | ModelAM Nova 2 LiteAmazon | Score24.6% | Percentile0.0% | Participants33 | EvidenceC | Evaluated |
MCP Atlas Highlights
The leading models and scores on this benchmark.
MCP Atlas Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MCP Atlas
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mcp atlas AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MEMuse Spark 1.1Meta
- Score
- 88.1%
- Price
- $1.3 input / $4.3 output per 1M tokens
- Speed
- Up to 6.2 tok/s via Meta Model API
Strengths
- Ranks #1 of 33 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MCP Atlas, not total model capability
- 02MAKimi K3Moonshot AI
- Score
- 84.2%
- Price
- $3.0 input / $15 output per 1M tokens
- Speed
- Up to 26 tok/s via Fireworks
Strengths
- Ranks #2 of 33 compared models
- 97th percentile on this benchmark
- C evidence result
Considerations
- This result measures MCP Atlas, not total model capability
- 03BYSeed 2.1 ProByteDance
- Score
- 83.8%
Strengths
- Ranks #3 of 33 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures MCP Atlas, not total model capability
- 04GOGemini 3.5 FlashGoogle
- Score
- 83.6%
- Price
- $1.5 input / $9.0 output per 1M tokens
- Speed
- Up to 1.2 tok/s via Google
Strengths
- Ranks #4 of 33 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures MCP Atlas, not total model capability
- 05ANClaude Opus 4.8Anthropic
- Score
- 82.2%
- Price
- $5.0 input / $25 output per 1M tokens
- Speed
- Up to 46 tok/s via Anthropic
Strengths
- Ranks #5 of 33 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures MCP Atlas, not total model capability
Selection summary
Best AI Models for MCP Atlas
Muse Spark 1.1 currently leads MCP Atlas with 88.1%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is MCP Atlas?
What MCP Atlas measures and how its scores work.
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MCP Atlas
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mcp-atlas|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MCP Atlas.
Which model scores highest on MCP Atlas?
Muse Spark 1.1 is currently ranked first with 88.1%.
What does MCP Atlas measure?
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
33 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.