Model comparison

GPT-6 Astra vs Mistral Large 3

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

Recorded profile verification October 2, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below

OpenAI

GPT-6 Astra

Frontier

Mistral

Mistral Large 3

Frontier · Open weights

AI model capability comparison
Specification	GPT-6 Astra	Mistral Large 3
Provider
Provider	OpenAI	Mistral
Tier
Tier	Frontier	Frontier
Context window
Context window	Winner: 1.05M	262K
Max output
Max output	128K	Not verifiedUnverified
Input / 1M tokens
Input / 1M tokens	$10	Winner: $0.50
Output / 1M tokens
Output / 1M tokens	$50	Winner: $1.50
Weights
Weights	Closed	Open
Parameters
Parameters	Not verifiedUnverified	675B total / 41B active (sparse MoE)
Reasoning levels
Reasoning levels	low, medium, high, xhigh, max	Not verifiedUnverified
Modalities
Modalities	text, image	text, image
License
License	Not verifiedUnverified	Apache 2.0
API model id
API model id	gpt-6-astra	mistral-large-2512
Released
Released	September 3, 2026	December 2, 2025
Artificial Analysis Intelligence Index [max] · source date GPT-6 Astra: 2026-10-01
Artificial Analysis Intelligence Index [max] · source date GPT-6 Astra: 2026-10-01	53	Not verifiedUnverified
Artificial Analysis Intelligence Index · source date Mistral Large 3: 2026-10-01
Artificial Analysis Intelligence Index · source date Mistral Large 3: 2026-10-01	Not verifiedUnverified	9
DeepSWE 1.1 · source date GPT-6 Astra: 2026-09-03
DeepSWE 1.1 · source date GPT-6 Astra: 2026-09-03	74.1	Not verifiedUnverified
OSWorld 2.0 (offline) · source date GPT-6 Astra: 2026-09-03
OSWorld 2.0 (offline) · source date GPT-6 Astra: 2026-09-03	72.6	Not verifiedUnverified
GPQA Diamond · source date GPT-6 Astra: 2026-09-03, Mistral Large 3: 2026-09-26 (comparability not verified)
GPQA Diamond · source date GPT-6 Astra: 2026-09-03, Mistral Large 3: 2026-09-26 (comparability not verified)	96	68
Humanity's Last Exam · source date GPT-6 Astra: 2026-09-03
Humanity's Last Exam · source date GPT-6 Astra: 2026-09-03	57.2	Not verifiedUnverified

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. 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.

Source date2026-10-01
Artificial Analysis (Mistral Large 3)
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check the cited source and its date.
Source date2026-10-01
Artificial Analysis (GPT-6 Astra (max))
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check the cited source and its date.
Source date2026-09-26
Artificial Analysis GPQA Diamond (independent; replaces Mistral's non-comparable base-model 5-shot 43.9)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
Source date2026-09-03
OpenAI GPT-6 Astra evaluation table (vendor-reported, with tools; maximum across evaluated efforts)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-09-03
OpenAI GPT-6 Astra evaluation table (vendor-reported; maximum across evaluated efforts)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
Source date2026-09-03
OpenAI (vendor-reported) (v2026.08.08 offline set, partial reward; vendor research/API evaluation, maximum across evaluated efforts)
Computer-use: completing real OS tasks (files, apps, settings) in a sandboxed desktop.
Comparable with caveatOffline vs live interaction modes are NOT comparable; step budgets and screen resolution must match.
Source date2026-09-03
OpenAI (xhigh, mini-swe-agent; matches Datacurve's independent board (74.1% at $4.43/task, rank 1; board updated 2026-09-22))
Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task.
Directly comparable

Pricing tiers

GPT-6 Astra: Standard $10/$50 per MTok (≤272K input); above 272K the full request bills $20/$75. Cached input $1/$2 and cache writes $12.50/$25 for short/long context. Batch/Flex are half Standard; Fast is 2x. Ultrafast is 6x: $60/$300 short, $120/$450 long, through Responses with global/US processing; no EU or other regional inference residency. Regional/FedRAMP processing adds 10% where eligible. Knowledge cutoff Apr 30 2026. Enterprise model access is disabled by default.

Mistral Large 3: Mistral first-party API $0.50/$1.50 per MTok; cached input $0.05. The 675B-total / 41B-active multimodal checkpoint declares Apache 2.0. Regional hosting is endpoint-specific.

FrontierRecord checked October 1, 2026

GPT-6 Astra

OpenAI describes GPT-6 Astra as 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

OpenAI places Astra at its Critical cybersecurity threshold and disables it by default for Enterprise. Tool calling requires Responses; none reasoning and custom temperature/top_p/logprobs are unsupported. Long prompts above 272K increase the full-request rate. GPT-6.1 Sol has lower base token prices; compare results on your own workload.

FrontierOpen weightsRecord checked October 2, 2026

Mistral Large 3

Mistral's December 2025 multimodal 675B/41B sparse MoE with a 256K context; Medium 3.5 is a separate dense model with configurable reasoning.

Best for

Open-weight deployments
Multimodal EU-hosted inference
Balanced frontier work

Watch out

The publisher describes Large 3 as not a dedicated reasoning model and documents vision limitations. It advertises FP8 deployment on a B200/H200 node or a separate NVFP4 checkpoint on H100/A100 nodes; this is not a guarantee for every serving setup. A separate hard output cap is not verified. Confirm regional residency on the actual endpoint.

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]

74.1%

Rows shown

Best source-matched Pass@1 per model

Snapshot date

2026-10-01

Mirrored from deepswe.datacurve.ai

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, output tokens and steps. Legacy v1 transcriptions are excluded here until an exact primary receipt is retained.

DeepSWE 1.1 leaderboard with pass rate, cost, tokens, and steps per task
#	Model	Pass@1	Cost / task	Tokens / task	Steps / task
1	GPT-6 Astra [xhigh]	74.1%	$4.43	30k	29
2	Gemini 3.8 Flash [high]	73.8%	$2.36	143k	166
3	Claude Opus 5 [max]	73.6%	$11.84	118k	99
4	GPT-5.6 Sol [max]	72.7%	$8.39	60k	61
5	Claude Fable 5 [xhigh]	69.9%	$13.41	80k	68
6	GPT-5.6 Terra [max]	69.6%	$4.95	72k	76
7	GLM 5.3 [max]	69.0%	$3.99	80k	124
8	Kimi K3 [max]	68.5%	$4.65	82k	98
9	Grok 4.6 [medium]	67.5%	$3.45	50k	70
10	GPT-5.6 Luna [max]	67.2%	$3.03	73k	102
11	GPT-5.5 [xhigh]	67.0%	$7.23	46k	82
12	Gemini 3.7 Flash [medium]	65.5%	$2.03	94k	117
13	GLM 5.3 Flash [max]	63.4%	$0.48	73k	123
14	DeepSeek V4-Pro [max]	62.8%	$0.24	106k	155
15	Claude Opus 4.8 [max]	59.0%	$13.22	135k	120
16	Qwen3.8-Max [xhigh]	57.5%	$3.73	95k	111
17	Muse Spark 1.2 [xhigh]	54.9%	$3.70	99k	101
18	Claude Sonnet 5 [max]	53.8%	$26.40	214k	268
19	Grok 4.5 [high]	53.8%	$2.42	36k	61
20	DeepSeek V4-Flash [max]	53.3%	$0.10	108k	153
21	Muse Spark 1.1 [xhigh]	53.3%	$2.36	74k	96
22	GPT-5.4 [xhigh]	51.8%	$5.65	71k	70
23	Gemini 3.6 Flash [high]	46.7%	$4.42	96k	117
24	GLM 5.2 [max]	43.8%	$3.92	78k	129
25	Gemini 3.5 Flash [high]	36.1%	$3.45	76k	105
26	Kimi K2.7 Code	30.5%	$2.82	59k	149
27	Claude Sonnet 4.6 [high]	29.9%	$5.52	76k	134
28	Gemini 3.1 Pro [high]	11.7%	$2.14	28k	76

“Best per model” shows each model’s highest source-matched Pass@1 in this capture; switch to all effort levels to see every retained configuration. Efforts differ across models, so this view is not a comparison at matched effort. The source was generated September 22 and captured October 1. Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.

When the cheaper one wins

Mistral Large 3 is cheaper on output at $1.50 per million tokens against $50 for GPT-6 Astra — about 33×. 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. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: Medium

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.
2/5 core specs verified on both sides — Not published for at least one side: max output, parameter count, reasoning levels.
No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
Verified within the last 90 days — Older of the two catalog checks was 25 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.

GPT-6 Astra: OpenAI model card — whole-profile source check October 1 (accessed 2026-10-01)
GPT-6 Astra: OpenAI current API pricing and processing tiers (accessed 2026-10-01)
GPT-6 Astra: OpenAI API changelog — September 3 release; checked October 1 (accessed 2026-10-01)
GPT-6 Astra: OpenAI — Introducing GPT-6 Astra (accessed 2026-09-03)
GPT-6 Astra: OpenAI API pricing (gpt-6-astra $10/$50) (accessed 2026-09-03)
GPT-6 Astra: CNBC — OpenAI launches GPT-6 Astra (accessed 2026-09-03)
GPT-6 Astra: OpenAI model docs — gpt-6-astra (128K max output, effort levels) (accessed 2026-09-05)
GPT-6 Astra: OpenAI API pricing (gpt-6-astra ≤272K $10/$50, >272K $20/$75) (accessed 2026-09-26)
Mistral Large 3: Current Mistral Large 3 API card (GA) (accessed 2026-10-01)
Mistral Large 3: Mistral pricing and exact cache rate (accessed 2026-10-01)
Mistral Large 3: Mistral Large 3 announcement (accessed 2026-10-01)
Mistral Large 3: Mistral changelog: identifier and release (accessed 2026-10-01)
Mistral Large 3: Large 3 official instruct checkpoint and Apache declaration (accessed 2026-10-01)

Related comparisons

Diving deeper on one model? GPT-6 Astra · Mistral Large 3

Common questions

GPT-6 Astra vs Mistral Large 3

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

Is GPT-6 Astra or Mistral Large 3 cheaper for input?

Mistral Large 3 is cheaper at $0.50 per million input tokens, against $10 for GPT-6 Astra — roughly 20× the price. Estimate both input and output token volume for your workload. These are base rates; GPT-6 Astra: Standard $10/$50 per MTok (≤272K input); above 272K the full request bills $20/$75. Cached input $1/$2 and cache writes $12.50/$25 for short/long context. Batch/Flex are half Standard; Fast is 2x. Ultrafast is 6x: $60/$300 short, $120/$450 long, through Responses with global/US processing; no EU or other regional inference residency. Regional/FedRAMP processing adds 10% where eligible. Knowledge cutoff Apr 30 2026. Enterprise model access is disabled by default. Mistral Large 3: Mistral first-party API $0.50/$1.50 per MTok; cached input $0.05. The 675B-total / 41B-active multimodal checkpoint declares Apache 2.0. Regional hosting is endpoint-specific.

Is GPT-6 Astra or Mistral Large 3 cheaper for output?

Mistral Large 3 is cheaper at $1.50 per million output tokens, against $50 for GPT-6 Astra — roughly 33× the price. Estimate both input and output token volume for your workload. These are base rates; GPT-6 Astra: Standard $10/$50 per MTok (≤272K input); above 272K the full request bills $20/$75. Cached input $1/$2 and cache writes $12.50/$25 for short/long context. Batch/Flex are half Standard; Fast is 2x. Ultrafast is 6x: $60/$300 short, $120/$450 long, through Responses with global/US processing; no EU or other regional inference residency. Regional/FedRAMP processing adds 10% where eligible. Knowledge cutoff Apr 30 2026. Enterprise model access is disabled by default. Mistral Large 3: Mistral first-party API $0.50/$1.50 per MTok; cached input $0.05. The 675B-total / 41B-active multimodal checkpoint declares Apache 2.0. Regional hosting is endpoint-specific.

Which has the larger context window, GPT-6 Astra or Mistral Large 3?

GPT-6 Astra accepts 1.05M tokens against 262K for Mistral Large 3. This only matters if you routinely send very long documents or large codebases.

Should I use GPT-6 Astra or Mistral Large 3?

Both are classified in our frontier tier; this editorial grouping does not imply equal capability. GPT-6 Astra is a candidate for computer-use agents; Mistral Large 3 is a candidate for open-weight deployments. Compare accuracy, tool reliability, latency and cost on representative tasks.

Can I self-host GPT-6 Astra or Mistral Large 3?

Mistral Large 3 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 Large 3 costs $0.50 per 1M tokens versus $10 for GPT-6 Astra — a 20x difference at the headline tier.
Context: GPT-6 Astra takes 1.05M against 262K for Mistral Large 3 — only decisive if your prompts approach the smaller window.
Deployment: Mistral Large 3 publishes weights you can self-host; the other is API-only.

Run the model picker Estimate stack cost All model comparisons

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