Benchmark Almanac

Enterprise-Bench L1-L2 v2

Not in model cards
Version 2

Agents answer 42 operational questions using six enterprise services. A GPT-6 Luna judge evaluates the final answer against task criteria.

On November 19, 2026, GPT-6.1 Sol with Codex led the Harbor leaderboard at 65.71% accuracy across 210 trials.

Made by
DevRev
Released
November 2026
Kind
Apps and MCP servers
Level
University
Scored
Graded by a model
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text, Actions
Interaction
Agentic
Environment
APIs and tools
Run by
Anyone
In views
Agents
Strongest model tested
Claude Opus 5.5 #5 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
2
Models scored on its own leaderboard

GPT-6.1 Sol leads with 65.7%

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.

  1. 1 GPT-6.1 Sol 65.7%
  2. 2 Claude Opus 5.5 31.9%

Source: Official Enterprise-Bench L1-L2 v2 leaderboard

#ModelScoreSettingAgent byReleasedRun onLinkSource
1 GPT-6.1 Sol 65.7% Codex OpenAI Sep 2026 Nov 2026 hub.harborframework.com Official leaderboard
2 Claude Opus 5.5 31.9% Claude Code Anthropic Sep 2026 Nov 2026 hub.harborframework.com Official leaderboard

Scores over time

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

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6.1 Sol Claude Opus 5.5 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-6.1 Sol Claude Opus 5.5

Source: Official Enterprise-Bench L1-L2 v2 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.

Versions

More in Tool use

All 265 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Neon 56.3%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%

Data audit

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (2 entries).
  • Note Models scored Only 2 models we track.
  • Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
  • Note Frontier models Only 2 of the top 10 have a score. The strongest tested is Claude Opus 5.5 (#5).
  • Pass Headroom The best is 65.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on hub.harborframework.com: 2 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