Benchmark Almanac

HarmEval

Llama-2 1.09% tops its leaderboard Mistral-7B-Instruct-v0.2 29.1% leads the models we track
Not in model cards

Models answer 550 harmful requests across 11 categories. A judge measures the share of unsafe responses.

The December 14, 2024 paper reports Llama 2 and Mistral. With simple prompts, SafeInfer on Llama 2 had the lowest unsafe response rate, 1.09%.

Released
June 2024
Kind
Refusing harmful requests
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
Kept private
Measures
Propensity
Behavior
Harmful use
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Content safety
Last model added
December 2023
Scores refreshed
November 20th, 2026
2
Entries in its paper, 1 model we track

Llama-2 tops the leaderboard with 1.09% Mistral-7B-Instruct-v0.2 leads with 29.1%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is Mistral-7B-Instruct-v0.2, at 29.1%. This view shows only models we track, each at its best.

  1. 1 Llama-2 Simple prompt, SafeInfer 1.09%
  2. 2 Mistral-7B-Instruct-v0.2 Simple prompt, SafeInfer 29.1%

Source: The HarmEval paper

Source: The HarmEval paper

#EntryScoreSettingDateSource
1 Llama-2 1.09% Simple prompt, SafeInfer Official leaderboard
2 Mistral-7B-Instruct-v0.2 29.1% Simple prompt, SafeInfer Dec 2023 Official leaderboard
#ModelScoreSettingDateSource
1 Mistral-7B-Instruct-v0.2 29.1% Simple prompt, SafeInfer Dec 2023 Official leaderboard

Number one over time

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

Mistral AI
Benchmark paper Not tested since Jun 2024

Source: The HarmEval paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Mistral-7B-Instruct-v0.2 Mistral-7B-Instruct-v0.2 Mistral-7B-Instruct-v0.2 0% 20% 40% 60% 80% 100% 2024 Mistral-7B-Instruct-v0.2 Mistral-7B-Instruct-v0.2

Source: Official HarmEval 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 Safety and alignment

All 636 in Safety and alignment
  • FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
  • StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is. Inkling 98.6%
  • Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. Gemini 4 Carbon 0%
  • Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior. Inkling 2 Mini 8.30%
  • Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions. Inkling 2 Small 4.70%
  • Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior. Inkling 2 Mini 9.80%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in December 2023, for Mistral-7B-Instruct-v0.2. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (2 entries).
  • Note Models scored Only 1 model we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in December 2023, for Mistral-7B-Instruct-v0.2.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 5 rows for models we track and 1 other entry 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