Benchmark Almanac

Mosaic Eval Gauntlet v0.3.0

Mistral 7B v0.1 0.52 leads since September 2023
Not in model cards

Models complete tasks across reading, reasoning, world knowledge, language understanding, and long context. MosaicML groups results by capability.

The repository documents the tasks and scoring groups for this revision.

Made by
MosaicML
Kind
Language reasoning
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
Run by
Anyone
Strongest model tested
Mistral 7B v0.1 #212 on the capability index
Last model added
September 2023
Scores refreshed
November 21st, 2026
16
Entries on its own leaderboard, 6 models we track

Mistral 7B v0.1 leads with 0.52 among models released by September 2023 Mistral 7B v0.1 leads with 0.52 among models released by September 2023

Best score per entry from the benchmark's own leaderboard, read on November 21st, 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 September 2023, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Mistral 7B v0.1 0.52
  2. 2 Falcon-40B 0.50
  3. 3 falcon-40b-instruct 0.50
  4. 4 Llama-2-13b-hf 0.48
  5. 5 Llama-2-13b-chat-hf 0.48
  6. 6 Mistral-7B-Instruct-v0.1 0.47
  7. 7 mpt-30b-instruct 0.47
  8. 8 MPT-30B 0.43
  9. 9 Llama-2-7b-chat-hf 0.42
  10. 10 Llama-2-7b-hf 0.40
  11. 11 mpt-7b-8k-instruct 0.36
  12. 12 mpt-7b-8k 0.35
  13. 13 mpt-7b-instruct 0.35
  14. 14 Falcon-7B 0.34
  15. 15 MPT-7B 0.32
  16. 16 falcon-7b-instruct 0.31

Source: Official Mosaic Eval Gauntlet v0.3.0 leaderboard

#EntryScoreSettingDateSource
1 Mistral 7B v0.1 0.52 Sep 2023 Official leaderboard
2 Falcon-40B 0.50 Mar 2023 Official leaderboard
3 falcon-40b-instruct 0.50 Official leaderboard
4 Llama-2-13b-hf 0.48 Official leaderboard
5 Llama-2-13b-chat-hf 0.48 Official leaderboard
6 Mistral-7B-Instruct-v0.1 0.47 Sep 2023 Official leaderboard
7 mpt-30b-instruct 0.47 Official leaderboard
8 MPT-30B 0.43 Jun 2023 Official leaderboard
9 Llama-2-7b-chat-hf 0.42 Official leaderboard
10 Llama-2-7b-hf 0.40 Official leaderboard
11 mpt-7b-8k-instruct 0.36 Official leaderboard
12 mpt-7b-8k 0.35 Official leaderboard
13 mpt-7b-instruct 0.35 Official leaderboard
14 Falcon-7B 0.34 Apr 2023 Official leaderboard
15 MPT-7B 0.32 May 2023 Official leaderboard
16 falcon-7b-instruct 0.31 Official leaderboard
#ModelScoreSettingDateSource
1 Mistral 7B v0.1 0.52 Sep 2023 Official leaderboard
2 Falcon-40B 0.50 Mar 2023 Official leaderboard
3 Mistral-7B-Instruct-v0.1 0.47 Sep 2023 Official leaderboard
4 MPT-30B 0.43 Jun 2023 Official leaderboard
5 Falcon-7B 0.34 Apr 2023 Official leaderboard
6 MPT-7B 0.32 May 2023 Official leaderboard

Rankings by part

We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as World knowledge, Commonsense reasoning and Language understanding. Mistral 7B v0.1 leads 4 of them, and Falcon-40B leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

World knowledge

6 models we track have a score here.

  1. 1 Mistral 7B v0.1 0.56
  2. 2 Falcon-40B 0.56
  3. 3 MPT-30B ↑1 0.49
  4. 4 Mistral-7B-Instruct-v0.1 ↓1 0.48
  5. 5 Falcon-7B 0.37
  6. 6 MPT-7B 0.36

2 models have held number one on the official leaderboard since 2023

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

Technology Innovation Institute Mistral AI
Own leaderboard Not tested since Sep 2023

Source: Official Mosaic Eval Gauntlet v0.3.0 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
0.30 0.40 0.50 2023 0.30 0.40 0.50 2023

Source: Official Mosaic Eval Gauntlet v0.3.0 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in September 2023, for Mistral-7B-Instruct-v0.1. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (16 entries).
  • Pass Models scored 6 models we track, plus 10 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in September 2023, for Mistral-7B-Instruct-v0.1.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Mistral 7B v0.1 (#212).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 6 rows for models we track and 10 other entries at the last read.
  • Pass Last read November 21st, 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