aiaimodel.cards
← All benchmarks

MCP-Atlas

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Muse Spark 1.2 · Metabest value
    90.3%
  2. 2Muse Spark 1.1 · Metabest value
    88.1%
  3. 3Claude Opus 4.8 · Anthropic
    82.2%
  4. 4Dola Seed 2.1 Turbo · ByteDancebest value
    80.3%
  5. 5Claude Opus 4.7 · Anthropic
    77.3%
  6. 6Gemini 3.1 Pro · Google
    69.2%
  7. 7Claude Opus 4.5 · Anthropic
    62.3%
  8. 8Claude Sonnet 4.6 · Anthropic
    61.3%
  9. 9Claude Opus 4.6 · Anthropic
    59.5%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Muse Spark 1.2 launch post charts; Muse Spark 1.2 & Muse Code evaluation methodology

    Values read from Meta's published bar charts. Terminal-Bench 2.1 and DeepSWE v1.1 run each model in its own agent product (Muse Code for 1.2, mini-swe-agent for 1.1, Claude Code, Codex, Grok Build, Antigravity CLI), pass@1 averaged over five attempts, so DeepSWE is not harness-identical to the official leaderboard. Muse Spark at xhigh, Opus 5 and GPT at max, Grok and Gemini at high. The MCP Atlas chart shows Opus 5 at xhigh and omits GPT 5.6 Terra, Grok 4.5 and Gemini 3.6 Flash. Meta Internal Coding Bench is 440 tasks from Meta's own codebase.

  • Muse Spark 1.1 model page; report §5

    Highest reasoning effort for every model (high for Gemini 3.1 Pro, max for Opus 4.8). "Muse Spark (1.0)" is the earlier model. Third-party scores are Meta's best-effort runs.

  • Claude Opus 4.8 Table 8.1.A, p.194–195

    Opus 4.8 uses adaptive thinking at max effort with default sampling, averaged over 5 trials. Competitor figures come from the developers' own published cards or leaderboards.

  • Dola Seed 2.1 Turbo Tables 1, 2, 5, 11 (pp.9, 10, 19, 53)

    ByteDance's own runs from the Seed2.1 model card. Seed 2.1 Pro (not on BytePlus) is shown for reference. ProgramBench is reported as the average pass rate.

  • Claude Opus 4.7 Table 8.1.A, p.191–192

    Opus 4.7 uses adaptive thinking at max effort with default sampling, averaged over 5 trials (Terminal-Bench 2.0 with thinking disabled; Finance Agent at high effort). Competitor figures come from the developers' own published cards or leaderboards.

  • Gemini 3.1 Pro p.4

    Results as of February 2026, Gemini at Thinking (High); competitors at their highest reported settings, as listed by Google.

  • Claude Opus 4.5 Table 2.3.A, p.19

    Average of 5 trials with a 64k thinking budget, 200k context, default (high) effort and default sampling. SWE-bench, τ²-bench and MCP Atlas are without extended thinking; Terminal-bench uses a 128k budget (57.8% at 64k). GPT-5.1 MMMU is from the MMMU leaderboard.

  • Claude Sonnet 4.6 Table 2.1.A, p.15

    Claude Sonnet 4.6 results are averaged over 10 trials (SWE-bench over 25) with adaptive thinking at max effort and default sampling; Terminal-Bench 2.0 at default thinking. ARC-AGI-2 is 60.4% at high effort. Competitor columns as reported in the card.

  • Claude Opus 4.6 Table 2.3.A, p.18

    Opus 4.6 results average 5 trials (SWE-bench: 25) with adaptive thinking at max effort and default sampling. MCP-Atlas is the max-effort score (62.7% at high). Gemini 3 Pro ARC-AGI-2 is Deep Thinking.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.