Benchmark Almanac

Vals Router Index

Nexus Auto with Sol 60% tops its leaderboard
Not in model cards

Model routers run all eight Vals Index v2.2 benchmarks through the same agents as single models and are scored with the Index weights.

The board had five routers on October 28th, 2026. It compares them with single-model Index runs.

Made by
Vals AI
Released
October 2026
Kind
Composite indices
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
6
Entries on its own leaderboard, 0 models we track

Nexus Auto with Sol tops the leaderboard with 60%

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 60.0 Nexus Auto with Sol
  2. 57.8 Router
  3. 56.5 Nexus Auto with Opus
  4. 55.6 Jev Router
  5. 52.2 Auto Router
  6. 48.1 Fugu Max
  1. 1 Nexus Auto with Sol 60%
  2. 2 Router 57.8%
  3. 3 Nexus Auto with Opus 56.5%
  4. 4 Jev Router 55.6%
  5. 5 Auto Router 52.2%
  6. 6 Fugu Max 48.1%

Source: Official Vals Router Index leaderboard

#EntryScoreSettingDateSource
1 Nexus Auto with Sol 60% Official leaderboard
2 Router 57.8% Official leaderboard
3 Nexus Auto with Opus 56.5% Official leaderboard
4 Jev Router 55.6% Official leaderboard
5 Auto Router 52.2% Official leaderboard
6 Fugu Max 48.1% Official leaderboard

Accuracy versus cost

The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.

50% 60% 70% 80% $0.1$1$10 Cost per test ($), log scale, lower is better Accuracy Nexus Auto with Opus: Accuracy 56.5%, cost per test $9.22. Not in our model list Jev Router: Accuracy 55.6%, cost per test $5.3. Not in our model list Fugu Max: Accuracy 48.1%, cost per test $3.91. Not in our model list Nexus Auto with Sol: Accuracy 60%, cost per test $1.25. Not in our model list Router: Accuracy 57.8%, cost per test $0.96. Not in our model list Auto Router: Accuracy 52.2%, cost per test $0.82. Not in our model list Nexus Auto with SolRouterAuto Router 50% 60% 70% 80% $0.1$1$10 Cost per test ($), log scale, lower is better Accuracy Nexus Auto with Opus: Accuracy 56.5%, cost per test $9.22. Not in our model list Jev Router: Accuracy 55.6%, cost per test $5.3. Not in our model list Fugu Max: Accuracy 48.1%, cost per test $3.91. Not in our model list Nexus Auto with Sol: Accuracy 60%, cost per test $1.25. Not in our model list Router: Accuracy 57.8%, cost per test $0.96. Not in our model list Auto Router: Accuracy 52.2%, cost per test $0.82. Not in our model list Nexus Auto with SolRouterAuto Router
ModelSettingAccuracyCost per test
Nexus Auto with Sol 60% $1.25
Router 57.8% $0.96
Nexus Auto with Opus 56.5% $9.22
Jev Router 55.7% $5.3
Auto Router 52.2% $0.82
Fugu Max 48.1% $3.91

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Other

All 43 in Other
  • Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
  • Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness. Gemini 4 Carbon 59.0
  • SAGE v1.1 (Vals) In use Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading. Claude Opus 5.5 91.3%
  • MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities. sonar 42%
  • Anthropic ECI (AECI) Only in system cards Index that combines a basket of capability benchmarks into one capability score to track trends across Anthropic models. Claude Opus 5.5 169.4
  • SPEED-Bench Only in system cards Measures speculative decoding across varied prompts and domains. Reports the average acceptance length of draft tokens, so higher means faster generation at the same output. Nemotron 3 Ultra 5.15