Shared benchmarks

17
Shared benchmarks for Muse Spark 1.2 and Muse Spark 1.3
BenchmarkMuse Spark 1.2Muse Spark 1.3
  • 36.4%
  • 58.6%xhigh
  • 47.6%max
Evaluation details for APEX-Agents Original

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on APEX-Agents Original

Muse Spark 1.3

Record for Muse Spark 1.3 on APEX-Agents Original
Record for Muse Spark 1.3 on APEX-Agents Original
  • 32.1%
  • 27.6%
Evaluation details for Chartography October 2026 leaderboard

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on Chartography October 2026 leaderboard

Muse Spark 1.3

Record for Muse Spark 1.3 on Chartography October 2026 leaderboard
  • 95.3%
  • 93.9%
Evaluation details for CharXiv Descriptive and reasoning — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 85.9%
  • 90.3%
Evaluation details for DeepSearchQA 900-prompt set

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on DeepSearchQA 900-prompt set

Muse Spark 1.3

Record for Muse Spark 1.3 on DeepSearchQA 900-prompt set
DeepSWE 1.1 — mini-swe-agentPotentially non-equivalent: Evaluator sets differ.
  • 55.0%1.1 — mini-swe-agent · DataCurve
  • 75.4%1.1 — mini-swe-agent · Meta
Potentially non-equivalent · Evaluation details for DeepSWE 1.1 — mini-swe-agent

Evaluator sets differ. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on DeepSWE 1.1 — mini-swe-agent

Muse Spark 1.3

Record for Muse Spark 1.3 on DeepSWE 1.1 — mini-swe-agent
  • 60.6%
  • 58.9%
Evaluation details for Finance Agent Benchmark 2 — October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 25.4%
  • 22.9%
Evaluation details for HLAB October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on Harvey's Legal Agent Benchmark October 2026 evaluation

Muse Spark 1.3

Record for Muse Spark 1.3 on Harvey's Legal Agent Benchmark October 2026 evaluation
  • 61.6%
  • 64.9%
Evaluation details for JobBench Main 65 tasks

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on JobBench Main 65 tasks

Muse Spark 1.3

Record for Muse Spark 1.3 on JobBench Main 65 tasks
  • 75.7%
  • 76.3%
Evaluation details for MedXpertQA MM — Mercor single-shot

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on MedXpertQA MM — Mercor single-shot

Muse Spark 1.3

Record for Muse Spark 1.3 on MedXpertQA MM — Mercor single-shot
  • 66.3%
  • 98.5%
Evaluation details for MRCR v2 8-needle 256K–512K (o200k_base)

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on MRCR v2 8-needle 256K–512K (o200k_base)

Muse Spark 1.3

Record for Muse Spark 1.3 on MRCR v2 8-needle 256K–512K (o200k_base)
  • 55.5%
  • 98.1%
Evaluation details for MRCR v2 8-needle 512K–1M (o200k_base)

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on MRCR v2 8-needle 512K–1M (o200k_base)

Muse Spark 1.3

Record for Muse Spark 1.3 on MRCR v2 8-needle 512K–1M (o200k_base)
  • 23.2%
  • 28.0%
Evaluation details for Riemann-bench October 2026 leaderboard

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on Riemann-bench October 2026 leaderboard

Muse Spark 1.3

Record for Muse Spark 1.3 on Riemann-bench October 2026 leaderboard
  • 46.2%
  • 59.4%
Evaluation details for SWE Atlas Codebase QnA — Public; mini-swe-agent

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

  • 69.7%
  • 72.3%
Evaluation details for Terminal-Bench 2.1 — Vals AI Terminus 2

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on Terminal-Bench 2.1 — Vals AI Terminus 2

Muse Spark 1.3

Record for Muse Spark 1.3 on Terminal-Bench 2.1 — Vals AI Terminus 2
  • 6.1%
  • 10.6%
Evaluation details for Terminal-Bench 4.0 — Vals AI mini-swe-agent

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Muse Spark 1.3

Record for Muse Spark 1.3 on Terminal-Bench 4.0 — Vals AI mini-swe-agent
  • 49.3%
  • 53.2%
Evaluation details for Vals Index 2.1

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.

Muse Spark 1.2

Record for Muse Spark 1.2 on Vals Index 2.1

Muse Spark 1.3

Record for Muse Spark 1.3 on Vals Index 2.1
  • 79.1%
  • 82.9%
Evaluation details for Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation

The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry.