ZMIME
Comparison · 3 models · Updated Nov 2, 2026

GPT-6.1 Terra vs Mistral Large 4 vs Claude Sonnet 5.5

GPT-6.1 Terra comes out ahead, 76 to 72 and 67 on our weighted score, though Mistral Large 4 is 48% cheaper per token.

  1. Our pick

    OpenAI

    GPT-6.1 Terra

    Released Oct 26, 2026New

    76/100
    • ECI168.1
    • Price$1.00 / $5.00
    • Context1.05M
    Full specs Remove GPT-6.1 Terra

  2. Mistral AI

    Mistral Large 4

    Released Oct 6, 2026NewBeta

    67/100
    • ECI150.6
    • Price$0.70 / $2.10
    • Context1.05M
    Full specs Remove Mistral Large 4

  3. Anthropic

    Claude Sonnet 5.5

    Released Sep 28, 2026New

    72/100
    • ECI166.7
    • Price$2.00 / $10.00
    • Context1M
    Full specs Remove Claude Sonnet 5.5
01 — Verdict

GPT-6.1 Terra is our pick

GPT-6.1 Terra is the better all-round choice, scoring 76/100 against Claude Sonnet 5.5 (72) and Mistral Large 4 (67). It leads on capability. Mistral Large 4 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-6.1 TerraCapabilities Index (ECI): GPT-6.1 Terra 168.1 · Claude Sonnet 5.5 166.7 · Mistral Large 4 150.6
  • Lowest priceMistral Large 4Mistral Large 4 $1.05 · GPT-6.1 Terra $2.00 · Claude Sonnet 5.5 $4.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-6.1 Terra and Mistral Large 4GPT-6.1 Terra 1,050,000 · Mistral Large 4 1,048,576 · Claude Sonnet 5.5 1,000,000 tokens
  • Widest inputsGPT-6.1 Terra and Claude Sonnet 5.5GPT-6.1 Terra: Text, Images, PDFs · Mistral Large 4: Text, Images · Claude Sonnet 5.5: Text, Images, PDFs
  • Self-hostingNo open weightsAll three are available only through APIs
How the score is built
MeasureWeightGPT-6.1 TerraMistral Large 4Claude Sonnet 5.5
CapabilityCapabilities Index (ECI)50%997797
Price25%344720
Inputs & features15%807080
Context window10%616160
Overall100%76/10067/10072/100
02 — Side by side

Every spec in one table

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

GPT-6.1 Terra vs Mistral Large 4 vs Claude Sonnet 5.5 specifications side by side
SpecificationGPT-6.1 TerraOpenAIMistral Large 4Mistral AIClaude Sonnet 5.5Anthropic
Capability
Capabilities Index (ECI)168.1 (best)150.6166.7
ECI rank#3 of 165 (best)#57 of 165#5 of 165
GPQA DiamondGraduate-level science questions94.3%88.1%95.6% (best)
FrontierMath Tiers 1–3Research-level mathematics90.9% (best)58.6%88.8%
OTIS Mock AIME 2024–2025Competition mathematics100% (best)98.3%100% (best)
SimpleQA VerifiedShort factual questions57.3% (best)20.0%46.5%
Price per million tokens
Input$1.00$0.70 (best)$2.00
Output$5.00$2.10 (best)$10.00
Cached input$0.05 (best)$0.07$0.10
Blended (3:1)$2.00$1.05 (best)$4.00
Long-context rateOver 272K: $2.00 / $7.50Same rateSame rate
Price sourceOfficial OpenAI APIOfficial Mistral APIOfficial Anthropic API
Limits
Context window1,050,000 tokens (best)1,048,576 tokens1,000,000 tokens
Max output128,000 tokens262,144 tokens (best)128,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningYeslow · medium · high · xhigh · maxYeslow · medium · highYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryProprietaryProprietary
API model IDgpt-6.1-terramistral-large-4claude-sonnet-5-5
API providers221534 (best)
ReleasedOct 26, 2026Oct 6, 2026Sep 28, 2026
Knowledge cutoffJun 1, 2026—Jun 2026
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.

  • GPT-6.1 Terra$20.00
  • Mistral Large 4$11.20
  • Claude Sonnet 5.5$40.00
04 — Questions

Which should you choose?

Which is better: GPT-6.1 Terra, Mistral Large 4 or Claude Sonnet 5.5?

GPT-6.1 Terra is the better all-round choice, scoring 76/100 against Claude Sonnet 5.5 (72) and Mistral Large 4 (67). It leads on capability. Mistral Large 4 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-6.1 Terra, Mistral Large 4 or Claude Sonnet 5.5?

Mistral Large 4 is cheaper at $0.70 input / $2.10 output per million tokens (official Mistral API price). GPT-6.1 Terra costs $1.00 input / $5.00 output per million tokens (official OpenAI API price); Claude Sonnet 5.5 costs $2.00 input / $10.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $1.05 per million tokens for Mistral Large 4 versus $2.00 for GPT-6.1 Terra (1.9× as much) and $4.00 for Claude Sonnet 5.5 (3.8× as much).

Which scores higher on benchmarks?

GPT-6.1 Terra scores higher on the Capabilities Index (ECI): GPT-6.1 Terra 168.1 (#3 of 165), Claude Sonnet 5.5 166.7 (#5 of 165) and Mistral Large 4 150.6 (#57 of 165). The confidence ranges of the top two overlap (164.9–172.9 vs 163.6–171.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — Claude Sonnet 5.5 95.6%, GPT-6.1 Terra 94.3%, Mistral Large 4 88.1%; FrontierMath Tiers 1–3 — GPT-6.1 Terra 90.9%, Claude Sonnet 5.5 88.8%, Mistral Large 4 58.6%; OTIS Mock AIME 2024–2025 — GPT-6.1 Terra 100%, Claude Sonnet 5.5 100%, Mistral Large 4 98.3%; SimpleQA Verified — GPT-6.1 Terra 57.3%, Claude Sonnet 5.5 46.5%, Mistral Large 4 20.0%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-6.1 Terra, Mistral Large 4 and Claude Sonnet 5.5 yet, so there is no like-for-like coding score. On overall capability, GPT-6.1 Terra 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?

GPT-6.1 Terra and Mistral Large 4 have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Sonnet 5.5. Maximum output per response: GPT-6.1 Terra up to 128,000, Mistral Large 4 up to 262,144, Claude Sonnet 5.5 up to 128,000 tokens.

Which can read images, PDFs, audio or video?

GPT-6.1 Terra accepts text, images and PDFs; Mistral Large 4 accepts text and images; Claude Sonnet 5.5 accepts text, images and PDFs. GPT-6.1 Terra handles the widest range of inputs.

Are any of these open source?

No. GPT-6.1 Terra, Mistral Large 4 and Claude Sonnet 5.5 are proprietary and only available through APIs and apps.

Which is newer?

GPT-6.1 Terra is the newest, released Oct 26, 2026. Mistral Large 4 came out Oct 6, 2026; Claude Sonnet 5.5 came out Sep 28, 2026. Knowledge cutoff: GPT-6.1 Terra Jun 1, 2026, Claude Sonnet 5.5 Jun 2026.

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