Skip to main content
AI Choice Engine

Model comparison

GPT-6 Astra vs Mistral Medium 3.5

OpenAI against Mistral, compared on context, price, and verified benchmark results.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

OpenAI

GPT-6 Astra

Frontier

vs

Mistral

Mistral Medium 3.5

Frontier · Open weights

AI model capability comparison
SpecificationGPT-6 AstraMistral Medium 3.5
ProviderOpenAIMistral
TierFrontierFrontier
Context windowWinner: 1.05M262K
Max output128KNot verifiedUnverified
Input / 1M tokens$10Winner: $1.50
Output / 1M tokens$50Winner: $7.50
WeightsClosedOpen
Parametersoverall flagship (reasoning, coding, computer use)128B dense
Reasoning levelslow, medium, high, xhigh, maxNot verifiedUnverified
Modalitiestext, imagetext, image
LicenseNot disclosedUnverifiedModified MIT
API model idgpt-6-astramistral-medium-3-5
ReleasedSeptember 3, 2026April 28, 2026
Artificial Analysis Intelligence Index [max] (2026-09-26)52.7Not verifiedUnverified
Artificial Analysis Intelligence Index (2026-09-26)Not verifiedUnverified14.2
DeepSWE 1.1 (2026-09-03)74.1Not verifiedUnverified
OSWorld 2.0 (offline) (2026-09-03)72.6Not verifiedUnverified
GPQA Diamond (2026-09-03)96Not verifiedUnverified
Humanity's Last Exam (2026-09-03)57.2Not verifiedUnverified
Terminal-Bench 4.0 [xhigh] (2026-09-26)59.6Not verifiedUnverified
Terminal-Bench 2.1 [xhigh] (2026-09-26)89.1Not verifiedUnverified

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Pricing tiers

GPT-6 Astra: Standard $10/$50 per MTok (≤272K input); above 272K input the whole request bills $20/$75. Cached input $1/MTok; cache writes $12.50 (1.25x input). Batch/Flex $5/$25. Fast mode costs 2x for up to 2x the speed ($20/$100 short context, $40/$150 long). Knowledge cutoff Apr 30 2026. Rolled out from 2026-09-03; Enterprise tenants get it disabled by default.

Mistral Medium 3.5: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense.

FrontierRecord checked September 26, 2026

GPT-6 Astra

GPT-6 Astra is OpenAI's overall flagship — its most capable model for complex reasoning, coding and computer use, and the first it gates at the Preparedness Framework's 'Critical' cybersecurity threshold.

Best for

  • Computer-use agents
  • Agentic coding
  • Hard reasoning

Watch out

Gated at the 'Critical' cyber threshold and disabled by default for Enterprise; long-context work bills $20/$75 above 272K input tokens. GPT-6 Sol ($2/$10) covers most work at a fifth of the price.

FrontierOpen weightsRecord checked September 26, 2026

Mistral Medium 3.5

Mistral Medium 3.5 is the model Mistral calls its new flagship — a 128B dense open-weight model with a 256K context, powering its Vibe remote agents.

Best for

  • EU-hosted frontier work
  • Open-weight self-hosting
  • Mistral Vibe agents

Watch out

Far behind US and Chinese frontier models on the Artificial Analysis index; max output is not published. Check the Modified MIT terms before redistribution.

Benchmark

DeepSWE 1.1 in context

Only GPT-6 Astra has a published DeepSWE 1.1 result. It is shown against the wider field, with cost per completed task alongside the score.

Local leader

GPT-6 Astra [xhigh]

74%

Rows shown

28

Best published Pass@1 per model (Datacurve's default view)

Snapshot date

2026-09-26

Mirrored from deepswe.datacurve.ai

DeepSWE 1.1 pass@10%16%32%48%64%80%$0$4.50$9.00$13.50$18.00$22.50$27.00Avg cost per taskGPT-6 Astra [xhigh]: 74% · $4.43 · 30k tokens · 29 stepsGemini 3.8 Flash [high]: 74% · $2.36 · 143k tokens · 166 stepsClaude Opus 5 [max]: 74% · $11.84 · 118k tokens · 99 stepsGPT-5.6 Sol [max]: 73% · $8.39 · 60k tokens · 61 stepsClaude Fable 5 [xhigh]: 70% · $13.41 · 80k tokens · 68 stepsGPT-5.6 Terra [max]: 70% · $4.95 · 72k tokens · 76 stepsGLM 5.3 [max]: 69% · $3.99 · 80k tokens · 124 stepsKimi K3 [max]: 69% · $4.65 · 82k tokens · 98 stepsGrok 4.6 [medium]: 68% · $3.45 · 50k tokens · 70 stepsGPT-5.6 Luna [max]: 67% · $3.03 · 73k tokens · 102 stepsGPT-5.5 [xhigh]: 67% · $7.23 · 46k tokens · 82 stepsGemini 3.7 Flash [medium]: 66% · $2.03 · 94k tokens · 117 stepsGLM 5.3 Flash [max]: 63% · $0.48 · 73k tokens · 123 stepsDeepSeek V4-Pro [max]: 63% · $0.24 · 106k tokens · 155 stepsClaude Opus 4.8 [max]: 59% · $13.22 · 135k tokens · 120 stepsQwen3.8-Max [xhigh]: 58% · $3.73 · 95k tokens · 111 stepsMuse Spark 1.2 [xhigh]: 55% · $3.70 · 99k tokens · 101 stepsClaude Sonnet 5 [max]: 54% · $26.40 · 214k tokens · 268 stepsGrok 4.5 [high]: 54% · $2.42 · 36k tokens · 61 stepsDeepSeek V4-Flash [max]: 53% · $0.10 · 108k tokens · 153 stepsMuse Spark 1.1 [xhigh]: 53% · $2.36 · 74k tokens · 96 stepsGPT-5.4 [xhigh]: 52% · $5.65 · 71k tokens · 70 stepsGemini 3.6 Flash [high]: 47% · $4.42 · 96k tokens · 117 stepsGLM 5.2 [max]: 44% · $3.92 · 78k tokens · 129 stepsGemini 3.5 Flash [high]: 36% · $3.45 · 76k tokens · 105 stepsKimi K2.7 Code: 31% · $2.82 · 59k tokens · 149 stepsClaude Sonnet 4.6 [high]: 30% · $5.52 · 76k tokens · 134 stepsGemini 3.1 Pro [high]: 12% · $2.14 · 28k tokens · 76 steps

Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost / tokens / steps; v1 uses published medians.

DeepSWE 1.1 leaderboard with pass rate, cost, tokens, and steps per task
#ModelPass@1Cost / taskTokens / taskSteps / task
1GPT-6 Astra [xhigh]74%$4.4330k29
2Gemini 3.8 Flash [high]74%$2.36143k166
3Claude Opus 5 [max]74%$11.84118k99
4GPT-5.6 Sol [max]73%$8.3960k61
5Claude Fable 5 [xhigh]70%$13.4180k68
6GPT-5.6 Terra [max]70%$4.9572k76
7GLM 5.3 [max]69%$3.9980k124
8Kimi K3 [max]69%$4.6582k98
9Grok 4.6 [medium]68%$3.4550k70
10GPT-5.6 Luna [max]67%$3.0373k102
11GPT-5.5 [xhigh]67%$7.2346k82
12Gemini 3.7 Flash [medium]66%$2.0394k117
13GLM 5.3 Flash [max]63%$0.4873k123
14DeepSeek V4-Pro [max]63%$0.24106k155
15Claude Opus 4.8 [max]59%$13.22135k120
16Qwen3.8-Max [xhigh]58%$3.7395k111
17Muse Spark 1.2 [xhigh]55%$3.7099k101
18Claude Sonnet 5 [max]54%$26.40214k268
19Grok 4.5 [high]54%$2.4236k61
20DeepSeek V4-Flash [max]53%$0.10108k153
21Muse Spark 1.1 [xhigh]53%$2.3674k96
22GPT-5.4 [xhigh]52%$5.6571k70
23Gemini 3.6 Flash [high]47%$4.4296k117
24GLM 5.2 [max]44%$3.9278k129
25Gemini 3.5 Flash [high]36%$3.4576k105
26Kimi K2.7 Code31%$2.8259k149
27Claude Sonnet 4.6 [high]30%$5.5276k134
28Gemini 3.1 Pro [high]12%$2.1428k76

“Best per model” shows each model’s highest published Pass@1, as Datacurve’s own board does; switch to all effort levels to see every configuration. Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.

When the cheaper one wins

Mistral Medium 3.5 is cheaper on output at $7.50 per million tokens against $50 for GPT-6 Astra — about 6.7×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 3/5 core specs verified on both sides — Not published for at least one side: max output, reasoning levels.
  • 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 days — Newest catalog check was 2 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? GPT-6 Astra · Mistral Medium 3.5

Common questions

GPT-6 Astra vs Mistral Medium 3.5

Answered from the verified figures on this page rather than general guidance.

Is GPT-6 Astra or Mistral Medium 3.5 cheaper for input?
Mistral Medium 3.5 is cheaper at $1.50 per million input tokens, against $10 for GPT-6 Astra — roughly 6.7× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-6 Astra has tiered pricing: Standard $10/$50 per MTok (≤272K input); above 272K input the whole request bills $20/$75. Cached input $1/MTok; cache writes $12.50 (1.25x input). Batch/Flex $5/$25. Fast mode costs 2x for up to 2x the speed ($20/$100 short context, $40/$150 long). Knowledge cutoff Apr 30 2026. Rolled out from 2026-09-03; Enterprise tenants get it disabled by default. Mistral Medium 3.5 has tiered pricing: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense.
Is GPT-6 Astra or Mistral Medium 3.5 cheaper for output?
Mistral Medium 3.5 is cheaper at $7.50 per million output tokens, against $50 for GPT-6 Astra — roughly 6.7× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-6 Astra has tiered pricing: Standard $10/$50 per MTok (≤272K input); above 272K input the whole request bills $20/$75. Cached input $1/MTok; cache writes $12.50 (1.25x input). Batch/Flex $5/$25. Fast mode costs 2x for up to 2x the speed ($20/$100 short context, $40/$150 long). Knowledge cutoff Apr 30 2026. Rolled out from 2026-09-03; Enterprise tenants get it disabled by default. Mistral Medium 3.5 has tiered pricing: Mistral first-party API $1.50/$7.50 per MTok; Mistral advertises up to 90% off cached input (exact cached rate not verified). Open weights under a Modified MIT licence. 128B dense.
Which has the larger context window, GPT-6 Astra or Mistral Medium 3.5?
GPT-6 Astra accepts 1.05M tokens against 262K for Mistral Medium 3.5. This only matters if you routinely send very long documents or large codebases.
Should I use GPT-6 Astra or Mistral Medium 3.5?
Both sit in the frontier tier, so the choice usually comes down to price and context rather than capability. GPT-6 Astra suits computer-use agents; Mistral Medium 3.5 suits eu-hosted frontier work.
Can I self-host GPT-6 Astra or Mistral Medium 3.5?
Mistral Medium 3.5 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. GPT-6 Astra is a closed model whose supported access paths are controlled by its provider.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: Mistral Medium 3.5 costs $1.50 per 1M tokens versus $10 for GPT-6 Astra — a 6.7x difference at the headline tier.
  • Context: GPT-6 Astra takes 1.05M against 262K for Mistral Medium 3.5 — only decisive if your prompts approach the smaller window.
  • Measured capability: GPT-6 Astra leads Artificial Analysis Intelligence Index 52.7 to 14.2 (measured 2026-09-26).
  • Deployment: Mistral Medium 3.5 publishes weights you can self-host; the other is API-only.
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.