Mistral Large 2.1

Mistral Large 2.1 has no overall index value yet because there are too few independent benchmark results.

PopularityRank 482 of 785

32out of 100+4 vs. last month

based on search, usage and attention

Summary

Mistral Large 2.1 is the 123B text checkpoint released at the end of 2024, with 131,000 tokens of context and function calls. Its model card covers demanding text and coding work but no multimodal input.

Mistral released Large 2.1 under the Mistral Research License for research and education. Commercial use requires a separate commercial license.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 99 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AIME: AIME 2024 (Show measurement, test conditions, and source)

Source value: 11.667
Score: 11.667
Metric: accuracy
Unit: %
Benchmark version: 1
Category: math
Task: aime_2024
Task label: AIME 2024
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-04-16. Temperature: 0.7. Latency in seconds: 21.843. Standard error: 0.891. Cost per task in USD: 0.006976. Source ID: vals-ai. Evidence capture ID: vals-aime-2026-11-07-0502ac25fa12. Source payload hash: 0502ac25fa12a66995187469cc5df841cb64b0f0a80a53a3cf2993c3a7bd1ab8. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-aime:1:aime_2024
Comparison methodology: Temperature: 0.7
Context: This benchmark is retained as archived evidence. The historical result is not interchangeable with an active leaderboard.

Source Vals AI

AIME: AIME 2025 (Show measurement, test conditions, and source)

Source value: 6.667
Score: 6.667
Metric: accuracy
Unit: %
Benchmark version: 1
Category: math
Task: aime_2025
Task label: AIME 2025
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-04-16. Temperature: 0.7. Latency in seconds: 17.509. Standard error: 1.992. Cost per task in USD: 0.0057. Source ID: vals-ai. Evidence capture ID: vals-aime-2026-11-07-0502ac25fa12. Source payload hash: 0502ac25fa12a66995187469cc5df841cb64b0f0a80a53a3cf2993c3a7bd1ab8. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-aime:1:aime_2025
Comparison methodology: Temperature: 0.7
Context: This benchmark is retained as archived evidence. The historical result is not interchangeable with an active leaderboard.

Source Vals AI

AIME: Overall (Show measurement, test conditions, and source)

Source value: 9.167
Score: 9.167
Metric: accuracy
Unit: %
Benchmark version: 1
Category: math
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-04-16. Temperature: 0.7. Latency in seconds: 19.676. Standard error: 1.091. Cost per task in USD: 0.006338. Source ID: vals-ai. Evidence capture ID: vals-aime-2026-11-07-0502ac25fa12. Source payload hash: 0502ac25fa12a66995187469cc5df841cb64b0f0a80a53a3cf2993c3a7bd1ab8. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-aime:1:overall
Comparison methodology: Temperature: 0.7
Context: This benchmark is retained as archived evidence. The historical result is not interchangeable with an active leaderboard.

Source Vals AI

GPQA Diamond: Few-Shot CoT (Show measurement, test conditions, and source)

Source value: 46.97
Score: 46.97
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: diamond_few_shot_cot
Task label: Few-Shot CoT
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: superseded
Retrieved at: 2026-10-16
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 16.517. Standard error: 3.547. Cost per task in USD: 0.008783. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-10-16-951eb5224097. Source payload hash: 951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077. Parser version: vals-astro-v3. Imported at: 2026-10-16. Source cohort: vals-gpqa:1:diamond_few_shot_cot
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Vals AI

GPQA Diamond: Few-Shot CoT (Show measurement, test conditions, and source)

Source value: 46.97
Score: 46.97
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: diamond_few_shot_cot
Task label: Few-Shot CoT
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 16.517. Standard error: 3.547. Cost per task in USD: 0.008783. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-11-07-8b1d0db37550. Source payload hash: 8b1d0db37550866d95b3f13c61381794328a046b6cf4d0fcaee3823d84421d9a. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-gpqa:1:diamond_few_shot_cot
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000

Source Vals AI

GPQA Diamond: Zero-Shot CoT (Show measurement, test conditions, and source)

Source value: 48.485
Score: 48.485
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: diamond_zero_shot_cot
Task label: Zero-Shot CoT
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: superseded
Retrieved at: 2026-10-16
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 15.087. Standard error: 3.523. Cost per task in USD: 0.004644. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-10-16-951eb5224097. Source payload hash: 951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077. Parser version: vals-astro-v3. Imported at: 2026-10-16. Source cohort: vals-gpqa:1:diamond_zero_shot_cot
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Vals AI

GPQA Diamond: Zero-Shot CoT (Show measurement, test conditions, and source)

Source value: 48.485
Score: 48.485
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: diamond_zero_shot_cot
Task label: Zero-Shot CoT
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 15.087. Standard error: 3.523. Cost per task in USD: 0.004644. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-11-07-8b1d0db37550. Source payload hash: 8b1d0db37550866d95b3f13c61381794328a046b6cf4d0fcaee3823d84421d9a. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-gpqa:1:diamond_zero_shot_cot
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000

Source Vals AI

GPQA Diamond: Overall (Show measurement, test conditions, and source)

Source value: 47.728
Score: 47.728
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: superseded
Retrieved at: 2026-10-16
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 15.802. Standard error: 2.5. Cost per task in USD: 0.006714. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-10-16-951eb5224097. Source payload hash: 951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077. Parser version: vals-astro-v3. Imported at: 2026-10-16. Source cohort: vals-gpqa:1:overall
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Vals AI

GPQA Diamond: Overall (Show measurement, test conditions, and source)

Source value: 47.728
Score: 47.728
Metric: accuracy
Unit: %
Benchmark version: 1
Category: reasoning
Task: overall
Task label: Overall
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 15.802. Standard error: 2.5. Cost per task in USD: 0.006714. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-11-07-8b1d0db37550. Source payload hash: 8b1d0db37550866d95b3f13c61381794328a046b6cf4d0fcaee3823d84421d9a. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-gpqa:1:overall
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000

Source Vals AI

LiveCodeBench: Easy (Show measurement, test conditions, and source)

Source value: 81.677
Score: 81.677
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: easy
Task label: Easy
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: superseded
Retrieved at: 2026-10-16
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 3.616. Standard error: 2.156. Cost per task in USD: 0.002239. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-10-16-1a7c7dabc9d9. Source payload hash: 1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5. Parser version: vals-astro-v3. Imported at: 2026-10-16. Source cohort: vals-lcb:1:easy
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Vals AI

LiveCodeBench: Easy (Show measurement, test conditions, and source)

Source value: 81.677
Score: 81.677
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: easy
Task label: Easy
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: active
Retrieved at: 2026-11-07
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 3.616. Standard error: 2.156. Cost per task in USD: 0.002239. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-11-07-281f362d312b. Source payload hash: 281f362d312b111e67659f4a8fa3a5bebbae36153db0f3750069e57f71536250. Parser version: vals-astro-v4. Imported at: 2026-11-07. Source cohort: vals-lcb:1:easy
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000

Source Vals AI

LiveCodeBench: Hard (Show measurement, test conditions, and source)

Source value: 4
Score: 4
Metric: accuracy
Unit: %
Benchmark version: 1
Category: coding
Task: hard
Task label: Hard
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Vals AI
Status: superseded
Retrieved at: 2026-10-16
Methodology: Source model ID: mistralai/mistral-large-2411. Source model name: Mistral Large 2.1. Provider reported by source: Mistral AI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Temperature: 0.7. Maximum output tokens: 256000. Latency in seconds: 6.776. Standard error: 1.047. Cost per task in USD: 0.004168. Source ID: vals-ai. Evidence capture ID: vals-lcb-2026-10-16-1a7c7dabc9d9. Source payload hash: 1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5. Parser version: vals-astro-v3. Imported at: 2026-10-16. Source cohort: vals-lcb:1:hard
Comparison methodology: Temperature: 0.7. Maximum output tokens: 256000
Context: This result is retained as historical evidence and is not interchangeable with current results.

Source Vals AI

Page 1 of 9

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

GPT-6 Astra83

Claude Haiku 5.577

GPT-6 Sol73

GPT-573

DeepSeek V4.1 Flash 101769

Kimi K367

MiniCPM-V 4.7 35B-A3B63

Mistral Large 2.132

DeepSeek V4.1 Flash 1017

MiniCPM-V 4.7 35B-A3B

GPT-6.1 Sol

Claude Opus 5

Qwen 3.8 Flash

Mistral Large 2.1

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 7, 2026

Mistral Large 2.1Amazon Nova Lite 32KAT-Coder-Pro V2.5 32ZwZ2-27B 32Granite Code 34B 32

Method changes in the timeline, a jump at these points is no market event:

1November 1, 2026: Value only with search or usage data, 30-day attention

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

Similar models

More models of the same kind as Mistral Large 2.1, chosen by model line, developer, size, price and release date.

All specifications

Architecture

Parameters: 123 billion; Source: Parameters
Knowledge cutoff: November 2024; Source: Knowledge cutoff

Input and output

Context window: 131,072 tokens; Source: Context window
Maximum output: 16,384 tokens; Source: Maximum output
Inputs: Text; Source: Inputs
Outputs: Text; Source: Outputs
Tool calling: Yes; Source: Tool calling

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

Weights: Open weights; Source: Weights
Access: API; Source: Access
License: Mistral Research License; Source: License

Frequently asked questions about Mistral Large 2.1

What is the knowledge cutoff of Mistral Large 2.1?

November 2024, according to Mistral AI. That is the month of release.

Stated by Mistral AI

NovKnowledge cutoffNovember 2024ReleasedNov 18, 2024

How large is the context window of Mistral Large 2.1?

131,072 tokens. That is how much text Mistral Large 2.1 reads at once, about 200 A4 pages.

Page count as a rule of thumb from Artificial Analysis

Context windowTokens the model reads at once · higher is better

GLM-5.1200K

DeepSeek-V3 0324164K

Mistral Large 2.1Rank 94 of 103131K

GLM-4.5131K

GPT OSS 120B131K

DeepSeek-V3.2128K

DeepSeek-R1128K

Can I run Mistral Large 2.1 locally?

Yes, the weights are open. With 123B parameters it needs a lot of memory, more a server than a laptop.

Stated by Mistral AI

Open weights: yes
License: Mistral Research License
Parameters: 123B
active per token: n/a

Sources and data date

Show all 25 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

Evaluator	Test series	Composite indices	Recorded active measurements
Vals AI	8	0	48
LMArena	0	0	1

Without vendor claims and historical or disputed results; those stay labelled in the single values. 1 measurements are not yet assigned to a test series.

Type	Evidence and data date
Input	Documented modalities. Retrieved October 27, 2026. Source: models.dev catalog · models.dev catalog (retrieved October 27, 2026)
Output	Documented modalities. Retrieved October 27, 2026. Source: models.dev catalog · models.dev catalog (retrieved October 27, 2026)
Research status	Research date October 15, 2026. 8 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published	vendor-benchmark-table Note The checked exact vendor release documentation and model card did not publish a numeric benchmark table. Independent Vals AI measurements are attached separately through the exact mistralai/mistral-large-2411 identity. Earlier Mistral Large checkpoints were not substituted.
Not published	mmlu-pro-evaluation-date-denominator-and-uncertainty Note The current card and pinned leaderboard record agree on the score, but the result record has no evaluation timestamp, exact scored denominator, or confidence interval.
Additional source	Hugging Face (retrieved October 15, 2026; October 17, 2026) · Mistral Large 2.1 model card · Editorial description reviewed October 2, 2026
Additional source	Vals AI (retrieved November 7, 2026)1 2 3 4 5
Additional source	Vals AI (retrieved October 16, 2026; November 7, 2026)1 2 3
Additional source	TIGER-Lab MMLU-Pro leaderboard record via EvalEval (retrieved October 17, 2026)
Additional source	LiveOIBench paper preprint, Table A9 (retrieved October 17, 2026)
Additional source	Vectara Hallucination Leaderboard (retrieved October 17, 2026)
Additional source	LongTableBench, Findings of the Association for Computational Linguistics: EMNLP 2025 (retrieved October 18, 2026)
Additional source	Arena Text Arena (retrieved October 18, 2026)
Additional source	Who Gets Which Message? Auditing Demographic Bias in LLM-Generated Targeted Text (retrieved October 19, 2026)
Additional source	Model metadata (retrieved October 15, 2026) · Mistral Large 2.1 model documentation · Editorial description reviewed October 2, 2026
Additional source	Mistral model overview · Editorial description reviewed October 2, 2026
Additional source	Mistral Large 2.1 hosted catalog record · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0