ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Claude Haiku 3.5 vs DeepSeek-V3 vs Mistral Large 2.1

Too close to call on our weighted score (DeepSeek-V3 49, Claude Haiku 3.5 46, Mistral Large 2.1 38). The right pick depends on what you value most.

  1. Anthropic

    Claude Haiku 3.5

    Released Oct 22, 2024

    46/100
    • ECI127.0
    • Price$0.80 / $4.00
    • Context200K
    Full specs Remove Claude Haiku 3.5

  2. DeepSeek

    DeepSeek-V3

    Released Dec 26, 2024

    49/100
    • ECI132.3
    • Price$0.32 / $1.10
    • Context131K
    Full specs Remove DeepSeek-V3

  3. Mistral AI

    Mistral Large 2.1

    Released Nov 18, 2024

    38/100
    • ECI128.6
    • Price$2.00 / $6.00
    • Context131K
    Full specs Remove Mistral Large 2.1
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 3 points (DeepSeek-V3 49/100, Claude Haiku 3.5 46/100, Mistral Large 2.1 38/100), so choose by what matters most for your work: DeepSeek-V3 for raw capability and Claude Haiku 3.5 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek-V3Capabilities Index (ECI): DeepSeek-V3 132.3 · Mistral Large 2.1 128.6 · Claude Haiku 3.5 127.0
  • Lowest priceDeepSeek-V3DeepSeek-V3 $0.515 · Claude Haiku 3.5 $1.60 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 3.5Claude Haiku 3.5 200,000 · DeepSeek-V3 131,072 · Mistral Large 2.1 131,072 tokens
  • Widest inputsClaude Haiku 3.5Claude Haiku 3.5: Text, Images, PDFs · DeepSeek-V3: Text · Mistral Large 2.1: Text
  • Self-hostingDeepSeek-V3 and Mistral Large 2.1Publishes downloadable weights (DeepSeek Model License)
How the score is built
MeasureWeightClaude Haiku 3.5DeepSeek-V3Mistral Large 2.1
CapabilityCapabilities Index (ECI)50%485550
Price25%386126
Inputs & features15%602525
Context window10%322525
Overall100%46/10049/10038/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Claude Haiku 3.5 vs DeepSeek-V3 vs Mistral Large 2.1 specifications side by side
SpecificationClaude Haiku 3.5AnthropicDeepSeek-V3DeepSeekMistral Large 2.1Mistral AI
Capability
Capabilities Index (ECI)127.0132.3 (best)128.6
ECI rank#147 of 165#136 of 165 (best)#142 of 165
GPQA DiamondGraduate-level science questions38.1%56.5% (best)51.3%
OTIS Mock AIME 2024–2025Competition mathematics4.3%15.8% (best)7.8%
Price per million tokens
Input$0.80$0.32 (best)$2.00
Output$4.00$1.10 (best)$6.00
Cached input———
Blended (3:1)$1.60$0.515 (best)$3.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 8 providersMedian of 2 providers
Limits
Context window200,000 tokens (best)131,072 tokens131,072 tokens
Max output8,192 tokens8,192 tokens16,384 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenDeepSeek Model LicenseOpen
API model ID———
API providers48 (best)2
ReleasedOct 22, 2024Dec 26, 2024Nov 18, 2024
Knowledge cutoffJul 31, 2024—Nov 2024
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Claude Haiku 3.5$16.00
  • DeepSeek-V3$5.40
  • Mistral Large 2.1$32.00
04 — Questions

Which should you choose?

Which is better: Claude Haiku 3.5, DeepSeek-V3 or Mistral Large 2.1?

It is close. Our weighted score puts them within 3 points (DeepSeek-V3 49/100, Claude Haiku 3.5 46/100, Mistral Large 2.1 38/100), so choose by what matters most for your work: DeepSeek-V3 for raw capability and Claude Haiku 3.5 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Haiku 3.5, DeepSeek-V3 or Mistral Large 2.1?

DeepSeek-V3 is cheaper at $0.32 input / $1.10 output per million tokens (median across 8 API providers). Claude Haiku 3.5 costs $0.80 input / $4.00 output per million tokens (median across 3 API providers); Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.515 per million tokens for DeepSeek-V3 versus $1.60 for Claude Haiku 3.5 (3.1× as much) and $3.00 for Mistral Large 2.1 (5.8× as much).

Which scores higher on benchmarks?

DeepSeek-V3 scores higher on the Capabilities Index (ECI): DeepSeek-V3 132.3 (#136 of 165), Mistral Large 2.1 128.6 (#142 of 165) and Claude Haiku 3.5 127.0 (#147 of 165). The confidence ranges of the top two overlap (127.5–135.5 vs 124.3–130.7), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek-V3 56.5%, Mistral Large 2.1 51.3%, Claude Haiku 3.5 38.1%; OTIS Mock AIME 2024–2025 — DeepSeek-V3 15.8%, Mistral Large 2.1 7.8%, Claude Haiku 3.5 4.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 3.5, DeepSeek-V3 and Mistral Large 2.1 yet, so there is no like-for-like coding score. On overall capability, DeepSeek-V3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

Claude Haiku 3.5 has the largest context window at 200,000 tokens, against 131,072 for DeepSeek-V3 and 131,072 for Mistral Large 2.1. Maximum output per response: Claude Haiku 3.5 up to 8,192, DeepSeek-V3 up to 8,192, Mistral Large 2.1 up to 16,384 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 3.5 accepts text, images and PDFs; DeepSeek-V3 accepts text; Mistral Large 2.1 accepts text. Claude Haiku 3.5 handles the widest range of inputs.

Are any of these open source?

DeepSeek-V3 and Mistral Large 2.1 publishes its weights (DeepSeek Model License) and can be self-hosted; Claude Haiku 3.5 is proprietary.

Which is newer?

DeepSeek-V3 is the newest, released Dec 26, 2024. Mistral Large 2.1 came out Nov 18, 2024; Claude Haiku 3.5 came out Oct 22, 2024. Knowledge cutoff: Claude Haiku 3.5 Jul 31, 2024, Mistral Large 2.1 Nov 2024.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.

05 — Keep comparing

Related comparisons