Benchmark Almanac

ITSMBench

Grok 4.6 0.70 leads since August 2026
Not in model cards

Agents operate an IT service desk across 53 conversations with simulated colleagues. The verifier grades the resulting database state, including permissions and required actions.

The 15-task comparison available November 19, 2026 reports Claude Opus 4.8 alone. Resuming unfinished conversations raised its score from 0.00 to 0.33.

Made by
Vibrant Labs
Released
August 2026
Kind
Customer service
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text, Actions
Interaction
Agentic
Items from
Generated
Refresh
One fixed set
Run by
Anyone
Occupations
Computer and mathematical
In views
Agents, Robotics
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
16
Entries on its own leaderboard, 14 models we track

Grok 4.6 leads with 0.70 among models released by August 2026 Grok 4.6 leads with 0.70 among models released by August 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 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. This view shows only models we track, each at its best.

The newest model with a score here came out in August 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 Grok 4.6 pass^1 0.70
  2. 2 DeepSeek-V4-Pro pass^1 0.70
  3. 3 Claude Opus 4.8 pass^1; Claude Opus 4.8 medium adaptive 0.70
  4. 4 DeepSeek-V4-Flash pass^1 0.60
  5. 5 Qwen3.7-Max pass^1 0.60
  6. 6 Claude Fable 5 pass^1 0.60
  7. 7 Gemini 3.5 Flash pass^1 0.59
  8. 8 Kimi K3 pass^1 0.59
  9. 9 GLM-5p2 pass^1 0.55
  10. 10 Claude Opus 5 pass^1 0.54
  11. 11 GPT-5.6 pass^1; GPT-5.6 Luna 0.51
  12. 12 Gemma 4 31B IT pass^1 0.51
  13. 13 Muse Spark 1.1 pass^1 0.50
  14. 14 gpt-oss-120b pass^1 0.48
  15. 15 Qwen3.7-Plus pass^1 0.48
  16. 16 Nemotron 3 Ultra pass^1; Nemotron-3 Ultra NVFP4 0.22

Source: Official ITSMBench leaderboard

#EntryScoreSettingDateSource
1 Grok 4.6 0.70 pass^1 Aug 2026 Official leaderboard
2 DeepSeek-V4-Pro 0.70 pass^1 Apr 2026 Official leaderboard
3 Claude Opus 4.8 0.70 pass^1; Claude Opus 4.8 medium adaptive May 2026 Official leaderboard
4 DeepSeek-V4-Flash 0.60 pass^1 Apr 2026 Official leaderboard
5 Qwen3.7-Max 0.60 pass^1 May 2026 Official leaderboard
6 Claude Fable 5 0.60 pass^1 Jun 2026 Official leaderboard
7 Gemini 3.5 Flash 0.59 pass^1 May 2026 Official leaderboard
8 Kimi K3 0.59 pass^1 Jul 2026 Official leaderboard
9 GLM-5p2 0.55 pass^1 Official leaderboard
10 Claude Opus 5 0.54 pass^1 Jul 2026 Official leaderboard
11 GPT-5.6 0.51 pass^1; GPT-5.6 Luna Official leaderboard
12 Gemma 4 31B IT 0.51 pass^1 Apr 2026 Official leaderboard
13 Muse Spark 1.1 0.50 pass^1 Jul 2026 Official leaderboard
14 gpt-oss-120b 0.48 pass^1 Aug 2025 Official leaderboard
15 Qwen3.7-Plus 0.48 pass^1 Jun 2026 Official leaderboard
16 Nemotron 3 Ultra 0.22 pass^1; Nemotron-3 Ultra NVFP4 Jun 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Grok 4.6 0.70 pass^1 Aug 2026 Official leaderboard
2 DeepSeek-V4-Pro 0.70 pass^1 Apr 2026 Official leaderboard
3 Claude Opus 4.8 0.70 pass^1; Claude Opus 4.8 medium adaptive May 2026 Official leaderboard
4 DeepSeek-V4-Flash 0.60 pass^1 Apr 2026 Official leaderboard
5 Qwen3.7-Max 0.60 pass^1 May 2026 Official leaderboard
6 Claude Fable 5 0.60 pass^1 Jun 2026 Official leaderboard
7 Gemini 3.5 Flash 0.59 pass^1 May 2026 Official leaderboard
8 Kimi K3 0.59 pass^1 Jul 2026 Official leaderboard
9 Claude Opus 5 0.54 pass^1 Jul 2026 Official leaderboard
10 Gemma 4 31B IT 0.51 pass^1 Apr 2026 Official leaderboard
11 Muse Spark 1.1 0.50 pass^1 Jul 2026 Official leaderboard
12 gpt-oss-120b 0.48 pass^1 Aug 2025 Official leaderboard
13 Qwen3.7-Plus 0.48 pass^1 Jun 2026 Official leaderboard
14 Nemotron 3 Ultra 0.22 pass^1; Nemotron-3 Ultra NVFP4 Jun 2026 Official leaderboard

2 models have held number one on the official leaderboard since its release in August 2026

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

DeepSeek xAI
Own leaderboard Not tested since Aug 2026
Grok 4.6 0.70

Source: Official ITSMBench 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
0.20 0.40 0.60 0.80 2026 0.20 0.40 0.60 0.80 2026

Source: Official ITSMBench 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 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 (16 entries).
  • Pass Models scored 14 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from August 2026, for Grok 4.6.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on enterpriseworlds.vibrantlabs.com: 15 rows for models we track and 2 other entries 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