Model comparison · accepted catalogue facts 2026-11-22

Mistral Large 2407 vs Mistral Small 3

Neither model has both an equal-or-higher measured score and an equal-or-lower estimated price in this pair. Retaining your current model is a valid outcome.

Both models belong to the Mistral, Codestral, Devstral and Voxtral family. Inclusion does not recommend either model. This is a direct pair comparison; global frontier membership is not its verdict.

Mistral Large 2407

LMArena general · Elo · higher is better

Scale starts at 1040 Elo

1266.2

Balanced effective USD / 1M tokens · lower is better

$3.00/M

Mistral Small 3

LMArena general · Elo · higher is better

Scale starts at 1040 Elo

1233.6

Balanced effective USD / 1M tokens · lower is better

$0.058/M

In-Depth Analysis

Mistral Large 2407 vs Mistral Small 3: Measured Technical Breakdown

Comprehensive comparison across measured human-preference evaluation, effective production token costs, architectural limits, and migration trade-offs.

Measured Capability (LMArena)
Mistral Large 2407 leads by 32.6 Elo

Mistral Large 2407: 1266.2 ±3.91 · Mistral Small 3: 1233.6 ±5.88 Statistically significant preference separation

Cost Comparison Across Canonical Production Workloads

Rates represent effective cost per 1M tokens under standard token blends. Cached prompt reads are factored according to workload context reuse.

Workload & RatioMistral Large 2407Mistral Small 3Cost DifferenceAdvantage
Balanced 3 tokens in per 1 out$3.00 /1M tokens$0.058 /1M tokens$2.94 (98% diff)Mistral Small 3 costs less
Summarise Huge input, tiny output$1.69 /1M tokens$0.052 /1M tokens$1.64 (97% diff)Mistral Small 3 costs less
Chat Long cached system prompt$3.06 /1M tokens$0.062 /1M tokens$3.00 (98% diff)Mistral Small 3 costs less
Code gen Output dominates$4.26 /1M tokens$0.068 /1M tokens$4.19 (98% diff)Mistral Small 3 costs less
Agentic Context replayed each turn$1.53 /1M tokens$0.055 /1M tokens$1.47 (96% diff)Mistral Small 3 costs less

Architectural & Operational Specifications

SpecificationMistral Large 2407Mistral Small 3Operational Note
Context window131,072 tokens32,768 tokensMistral Large 2407 has a 4.0× larger context window
Max output generation104,857 tokens16,384 tokensMistral Large 2407 allows longer single-turn completions
Base input price$2.00 / 1M tokens$0.050 / 1M tokensMistral Small 3 input rate is cheaper
Base output price$6.00 / 1M tokens$0.080 / 1M tokensMistral Small 3 output rate is cheaper
Cached input price$0.200 / 1M tokensNot listed / standard rate—
Reasoning & thinking tokensStandard generationStandard generation—
Input modalitiestext, filetext—
Tool calling / function useSupportedNot listedMistral Large 2407 declares function calling / tool support
Open weights & licenceProprietary (API-only)Proprietary (API-only)—
Provider & reseller marketMistral · 3 provider offersMistral · 2 provider offers—

When to Choose Mistral Large 2407

  • Higher measured general capability (1266.2 Elo on human evaluation).
  • Larger context window (131,072 tokens) for long-document or repo-level context.
  • Higher maximum completion limit (104,857 tokens).
  • Broader multimodal input support: text, file.
  • Direct integration with Mistral tooling and API features.

When to Choose Mistral Small 3

  • Direct integration with Mistral tooling and API features.
Risks when moving from Mistral Large 2407 → Mistral Small 3:
  • Context window: 131,072 → 32,768 tokens.
  • Output limit: 104,857 → 16,384 tokens.
  • Tool use is not supported by the candidate.
  • file input is not supported by the candidate.

Compare · model decision

Choose two or three models

Inspect the differences, estimate your workload and keep the evidence. All standard catalogue models are available, including unrated ones.

Catalogue facts
2026-11-22

2 / 3 selected · 0 requirements
Open public comparison link
Public workload and requirements

These settings are included in the share link. The fixed-request scenario and private evaluation data below are excluded.

A ↔ B

Neither model has both an equal-or-higher measured score and an equal-or-lower estimated price in this pair. Retaining your current model is a valid outcome.

Estimated blend: 75% input, 25% output; 0% cached input. Base context tier. Prompt length selects the billing tier. An unlisted cache-read rate uses that tier’s full input rate in this blend; missing required input or output rates prevent an estimate. The fixed-request estimate below validates actual context and output limits and requires a published cache-read rate when cache hits are assumed.

What changes between these models

Quality first, then estimated price. LMArena scores are human-preference measurements, not a benchmark of your application. A missing score is unrated.

  • Mistral Large 2407 · Meets the stated model requirements
  • Mistral Small 3 · Meets the stated model requirements
Material differences and unknown evidence. Deltas compare each model with model A. Unknown facts remain visible.
Measured factA Mistral Large 2407B Mistral Small 3
LMArena general score (Elo)1,266.21,233.6Δ vs A: -32.6 Elo
Score interval half-width (± Elo)3.915.88Δ vs A: +1.97 Elo
LMArena document score (Elo)UnknownUnknown
Estimated effective USD / 1M tokens$3$0.0575Δ vs A: -2.9425 USD/M
Base input USD / 1M tokens$2$0.05Δ vs A: -1.95 USD/M
Base output USD / 1M tokens$6$0.08Δ vs A: -5.92 USD/M
Base cached-input USD / 1M tokens$0.2Unknown
Context window (tokens)131,07232,768Δ vs A: -98,304 tokens
Output limit (tokens)104,85716,384Δ vs A: -88,473 tokens
Input modalitiestext, filetext
Tool useSupportedNot supportedΔ vs A: -1
Open weightsUnknownUnknown
Recorded licenceUnknownUnknown
Recorded retirement dateUnknownUnknown
6 shared measured facts
Shared measured facts. Deltas compare each model with model A. Unknown facts remain visible.
Measured factA Mistral Large 2407B Mistral Small 3
Benchmark reasoning effortdefaultdefault
ReasoningNot supportedNot supportedΔ vs A: 0
Model providerMistralMistral
Distinct sellers in the catalogue11Δ vs A: 0
Serving precision differs across offersNot supportedNot supportedΔ vs A: 0
Retirement evidenceNone announced; not a guaranteeNone announced; not a guarantee

Provider counts and precision flags describe catalogue offers. They do not establish the precision, availability, region, tool behaviour or limits of your chosen endpoint. Open each model’s provider table before switching.

Complete price ladders and billing conditions

Mistral Large 2407

Rates below are USD per 1M tokens. A threshold selects that whole input/output rate pair.

Input-token thresholdInputOutputCached input
Base, up to and including first threshold$2$6$0.2

Mistral Small 3

Rates below are USD per 1M tokens. A threshold selects that whole input/output rate pair.

Input-token thresholdInputOutputCached input
Base, up to and including first threshold$0.05$0.08Unknown
Migration preflight · compare each candidate with model A

Keeping Mistral Large 2407 is a valid decision. No pairwise comparison certifies a drop-in replacement.

Mistral Large 2407 → Mistral Small 3

Known loss or failed requirement

  • Context window: 131,072 → 32,768 tokens.
  • Output limit: 104,857 → 16,384 tokens.
  • Tool use is not supported by the candidate.
  • file input is not supported by the candidate.
  • Provider endpoint, serving precision, availability and task success need your own verification. Catalogue model capabilities do not certify an endpoint.
Check alternatives to Mistral Large 2407

Estimate a fixed request shape

Private to this tab unless you save locally or explicitly export private details. These are estimates, not observed invoices. Cross-model token counts and task success are assumptions.

0.1 extra attempts means 10 extra full attempts per 100 requests. Cache writes, tool charges, taxes and unlisted charges are excluded.

  • Mistral Large 2407Estimated total: $7 1,000 full attempts · base rates
  • Mistral Small 3Estimated total: $0.14 1,000 full attempts · base rates
Prompt and output sensitivity · sampled scenarios

Every point recalculates the entire request shape. Tier-boundary samples include one token below, at and above each threshold. Ordering between samples is not guaranteed. Lowest known cost excludes unknown estimates and is not a replacement recommendation.

Vary input; hold output, requests, cache and retries fixed.
Input tokensMistral Large 2407Mistral Small 3Coverage
2,000$7$0.14Lowest knownAll computed
4,096$11.192$0.2448Lowest knownAll computed
32,768$68.536Lowest knownineligibleInput plus output exceeds the published context window.Incomplete
131,072ineligibleInput plus output exceeds the published context window.ineligibleInput plus output exceeds the published context window.Incomplete
Vary output; hold input, requests, cache and retries fixed.
Output tokensMistral Large 2407Mistral Small 3
128$4.768$0.11024
2,048$16.288$0.26384
8,192$53.152$0.75536

Bring your observed evaluation results

JSON is parsed locally. Prompts, filenames, individual responses and extra fields are not retained. Import only aggregate measurements for selected models. Task/version labels do not establish that two evaluations used the same dataset.

Expected format
[{"model":"provider/exact-model-id","task":"support-answer","version":"rubric-1","attempts":100,"successes":84,"costUsd":2.4,"latencyMs":950}]

Use the exact catalogue ID. Replace the example values with observed measurements. Omit costUsd or latencyMs when they are unknown. No public score is inferred from these observations.

Keep the decision and its evidence

A portable record retains selected facts, complete tier ladders, public requirements and the publication manifest. It also embeds the full permitted public catalogue to verify the input artifact checksum. Files are larger for this reason (up to 2 MB); local storage is limited to 12 records. Team review is local to this browser; there is no hosted collaboration.

Saving is opt-in and includes private review fields. Shared comparison links never include them. Version 1 Check references remain separate and are not overwritten or guessed into this format.

Saved local decisions · 0

No version 2 decision records are stored in this browser.

Questions this page answers

Is Mistral Large 2407 a better-and-cheaper replacement for Mistral Small 3?

Neither model has both an equal-or-higher measured score and an equal-or-lower estimated price in this pair. Retaining your current model is a valid outcome.

Which model is higher rated: Mistral Large 2407 or Mistral Small 3?

Mistral Large 2407 scores higher on LMArena general (1266.2 ±3.9) compared to Mistral Small 3 (1233.6 ±5.9), a margin of 32.6 Elo points. The measured confidence intervals do not overlap, demonstrating a statistically significant preference lead on human evaluations.

Which model is more cost-effective: Mistral Large 2407 or Mistral Small 3?

On a standard balanced workload (3 prompt tokens per 1 generated token), Mistral Small 3 costs $0.058 per 1M tokens versus $3.00 for Mistral Large 2407. Mistral Large 2407 is approximately 52.2× the price of Mistral Small 3. Base input rates are $2.00 for Mistral Large 2407 and $0.050 for Mistral Small 3; base output rates are $6.00 for Mistral Large 2407 and $0.080 for Mistral Small 3.

How do their context windows and generation limits compare?

Mistral Large 2407 provides a 131,072-token context window with a maximum output limit of 104,857 tokens. Mistral Small 3 provides a 32,768-token context window with a maximum output of 16,384 tokens. Mistral Large 2407 offers a 4.0× larger context capacity, making it suitable for larger repositories and multi-document workflows.

What capabilities are lost when switching between Mistral Large 2407 and Mistral Small 3?

Switching from Mistral Large 2407 to Mistral Small 3 involves: Context window: 131,072 → 32,768 tokens; Output limit: 104,857 → 16,384 tokens; Tool use is not supported by the candidate; file input is not supported by the candidate. Run test suites on your specific prompt templates and tool declarations before cutting over production traffic.

Can Mistral Large 2407 or Mistral Small 3 be self-hosted or deployed privately?

Both Mistral Large 2407 and Mistral Small 3 are proprietary cloud models offered via managed API endpoints. Mistral Large 2407 is served by Mistral and 3 catalogue offers, while Mistral Small 3 is served by Mistral and 2 catalogue offers.

What is included in this comparison?

Accepted model capabilities, context and output limits, complete price-tier ladders, independent LMArena measurements and missing evidence. Provider endpoint precision and application success still need verification.

Can I compare a different workload or keep a decision record?

Yes. Change the public workload, prompt length and requirements in the comparison workspace. Fixed-request scenarios, aggregate evaluations and review notes stay local unless explicitly exported.

Evidence & Ask