Benchmark Almanac

Vals Inference Provider Index

DeepSeek V4.1 Flash 71.2% leads since November 2026
Not in model cards

Agents use different inference providers to complete the same finance, coding, and legal tasks.

Vals compares three underlying models across ten provider configurations and weights finance, coding, and legal accuracy equally.

Made by
Vals AI
Released
November 2026
Kind
Composite work indices
Level
Expert
Scored
Settled by events
Answers
Agent task
Tasks
Kept private
Measures
Capability
Language
English
In and out
Text, Code, Documents → Actions, Text, Code
Interaction
Agentic
Environment
Terminal, APIs and tools
Refresh
One fixed set
Run by
A host
Strongest model tested
Kimi K3 #25 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
3
Models scored on its own leaderboard

DeepSeek V4.1 Flash leads with 71.2% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 DeepSeek V4.1 Flash max 71.2%
  2. 2 Kimi K3 max 69.9%
  3. 3 MiniMax-M3 53.5%

Source: Official Vals Inference Provider Index leaderboard

#ModelScore ±SettingDateSource
1 DeepSeek V4.1 Flash 71.2% ±3 max, Fireworks AI Sep 2026 Official leaderboard
2 Kimi K3 69.9% ±3 max, Fireworks AI Jul 2026 Official leaderboard
3 MiniMax-M3 53.5% ±3.6 MiniMax Jun 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Finance Agent v2, Vibe Code Bench and Legal Research. Each ranks models on one part of the test. DeepSeek V4.1 Flash leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Finance Agent v2

3 models we track have a score here.

  1. 1 DeepSeek V4.1 Flash 60.2%
  2. 2 MiniMax-M3 ↑1 59.6%
  3. 3 Kimi K3 ↓1 59.3%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

DeepSeek
Own leaderboard 1 leader

Source: Official Vals Inference Provider Index leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) DeepSeek V4.1 Flash Kimi K3 MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) DeepSeek V4.1 Flash MiniMax-M3

Source: Official Vals Inference Provider Index leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (3 entries).
  • Note Models scored Only 3 models we track.
  • Pass Newest score The newest is from September 2026, for DeepSeek V4.1 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Kimi K3 (#25).
  • Pass Headroom The best is 71.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on vals.ai: 10 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check