Jamba 1.7 Large

Composite indexes

• Artificial Analysis Intelligence Index#137 of 151
  6independentIntelligence Index v4.3; non-reasoning; estimatedArtificial Analysis: Jamba 1.7 Large ↗

  Leader: Claude Opus 5.5 at 58

Coding

• LiveCodeBench#52 of 57
  18.1%independentnon-reasoningArtificial Analysis: Jamba 1.7 Large ↗

  Leader: Fugu at 92.9%

Agents and tool use

• τ²-Bench#78 of 89
  13.5%independenttelecom; non-reasoningArtificial Analysis: Jamba 1.7 Large ↗

  Leader: GLM-5.2 at 99.1%

Reasoning and knowledge

• GPQA Diamond#136 of 144
  39%independentnon-reasoningArtificial Analysis: Jamba 1.7 Large ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#150 of 153
  3.7%independentno tools; non-reasoningArtificial Analysis: Jamba 1.7 Large ↗

  Leader: Claude Sonnet 5.5 at 64.5%

• CritPt#136 of 144
  0%independentnon-reasoningArtificial Analysis: Jamba 1.7 Large ↗

  Leader: Muse Wonder Full at 33%

Vision and long context

• AA Long Context Reasoning#122 of 144
  19.3%independentnon-reasoningArtificial Analysis: Jamba 1.7 Large ↗

  Leader: Kimi K3 at 88.7%

Other published results