GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B

Comparison

As of August 25, 2026, GPT-5.1 Codex Mini and Qwen3.5-35B-A3B have the same blended API cost at $2.25 per 1 million input plus 1 million output tokens. GPT-5.1 Codex Mini is $0.25 / $2.00 per million tokens versus Qwen3.5-35B-A3B at $0.25 / $2.00. Sources: https://developers.openai.com/api/docs/pricing and https://bailian.console.aliyun.com/

Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); Qwen pricing (https://bailian.console.aliyun.com/)

GPT-5.1 Codex Mini

OpenAI

$2.25blended / 1M

Input

$0.25

Output

$2.00

400K ctx|Proprietary

Qwen3.5-35B-A3B

Qwen

$2.25blended / 1M

Input

$0.25

Output

$2.00

262.1K ctx|Open Source

GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B comparison

Token pricing, specs, and benchmarks side by side

Shared benchmarks

Each bar is share of the current leader on that eval. Click a row to open the board.

GPT-5.1 Codex MiniQwen3.5-35B-A3B

Score vs price

Arena Code Elo. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price.

Best score at each priceGPT-5.1 Codex MiniQwen3.5-35B-A3B

Metric

GPT-5.1 Codex Mini

Qwen3.5-35B-A3B

Provider

OpenAI

Qwen

License

Proprietary

Open Source

Release Date

2025-11-12

2026-02-24

Pricing (per 1M tokens)

Input Price0%

$0.25

Output Price0%

$2.00

Blended (1M + 1M)

$2.25

Model Details

Context Window

400K

262.1K

Max Output Tokens

128K

65K

Knowledge Cutoff

2024-09-30

N/A

Throughput

200 tok/s

N/A

Benchmarks

HLE

—

47.4%

GPQA

—

84.2%

SWE-bench Verified

—

69.2%

LiveCodeBench v6

—

74.6%

Arena Code Elo

1244

1250

BrowseComp

—

61%

IFEval

—

91.9%

IFBench

—

70.2%

AA-LCR

—

58.5%

ScreenSpot Pro

—

68.6%

Terminal-Bench

61.6%

—

Terminal-Bench 2.0

—

40.5%

OSWorld Verified

—

54.5%

MMMU-Pro

—

75.1%

MMMLU

—

85.2%

CharXiv-R

—

77.5%

AIME 2025

42.1%

—

MMMU

85.4%

81.4%

Ai2d

—

92.6%

Androidworld Sr

—

71.1%

Babyvision

—

38.4%

Bfcl V4

—

67.3%

Browsecomp Zh

—

69.5%

C Eval

—

90.2%

Cc Ocr

—

80.7%

Codeforces

—

82.2%

Countbench

—

97.8%

Deep Planning

—

22.8%

Dynamath

—

85%

Embspatialbench

—

83.1%

ERQA

—

64.8%

Fullstackbench En

—

58.1%

Fullstackbench Zh

—

55%

Global Piqa

—

86.6%

Hallusion Bench

—

67.9%

HMMT 2025

—

89%

Hmmt25

—

89.2%

Hypersim

—

13.1%

INCLUDE

—

79.7%

Lingoqa

—

79.2%

Longbench V2

—

59%

LVBench

—

71.4%

MathVision

—

83.9%

Mathvista Mini

—

86.2%

Maxife

—

86.6%

Medxpertqa

—

61.4%

Mlvu

—

85.6%

Mmbench V1 1

—

91.5%

Mmlongbench Doc

—

59.5%

MMLU-Pro

—

85.3%

Mmlu Prox

—

81%

MMLU-Redux

—

93.3%

Mmstar

—

81.9%

Mmvu

—

72.3%

Multichallenge

—

60%

Mvbench

—

74.8%

Nova 63

—

57.1%

Nuscene

—

14.6%

Ocrbench

—

91%

Odinw

—

42.6%

Ojbench

—

36%

Omnidocbench 1 5

—

89.3%

Pmc Vqa

—

62%

Polymath

—

64.4%

Realworldqa

—

84.1%

Refcoco Avg

—

89.2%

Refspatialbench

—

63.5%

Seal 0

—

41.4%

Simplevqa

—

58.3%

Slakevqa

—

78.7%

Sunrgbd

—

33.4%

SuperGPQA

—

63.4%

T2 Bench

—

81.2%

Terminal-Bench 2

—

40.5%

Tir Bench

—

55.5%

V Star

—

92.7%

Videomme W O Sub

—

82.5%

Videomme W Sub

—

86.6%

VideoMMMU

—

80.4%

Vita Bench

—

31.9%

Vlmsareblind

—

97%

Widesearch

—

57.1%

Wmt24

—

76.3%

Zerobench

—

Zerobench Sub

—

34.1%

Benchmark Wins

GPT-5.1 Codex Mini 1|1 Qwen3.5-35B-A3B

Verdict

GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B: the bottom line

Both models are closely matched on benchmarks. GPT-5.1 Codex Mini has the pricing advantage, making it the better value unless Qwen3.5-35B-A3B's specific capabilities are critical to your workflow.

View GPT-5.1 Codex Mini details View Qwen3.5-35B-A3B details

GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B FAQ

Which is cheaper, GPT-5.1 Codex Mini or Qwen3.5-35B-A3B?

As of August 25, 2026, GPT-5.1 Codex Mini is 0% cheaper on blended LLM API pricing. GPT-5.1 Codex Mini costs $0.25 per million input tokens and $2.00 per million output tokens ($2.25 blended 1M-in + 1M-out). Qwen3.5-35B-A3B costs $0.25 / $2.00 per million tokens ($2.25 blended). Sources: https://developers.openai.com/api/docs/pricing and https://bailian.console.aliyun.com/. The cheapest LLM for your app still depends on how many output tokens you generate.

How much does GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B cost per million tokens?

GPT-5.1 Codex Mini OpenAI API pricing is $0.25 input and $2.00 output per million tokens via OpenAI. Qwen3.5-35B-A3B Qwen API pricing is $0.25 input and $2.00 output per million tokens via Qwen. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.

Which is better for coding, GPT-5.1 Codex Mini or Qwen3.5-35B-A3B?

Qwen3.5-35B-A3B has a published SWE-bench Verified score of 69.2%. GPT-5.1 Codex Mini does not have that eval on this page yet.

What is the context window for GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B?

GPT-5.1 Codex Mini supports a 400K token context window, while Qwen3.5-35B-A3B supports 262K tokens. GPT-5.1 Codex Mini offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.

Which model performs better on benchmarks, GPT-5.1 Codex Mini or Qwen3.5-35B-A3B?

GPT-5.1 Codex Mini and Qwen3.5-35B-A3B are tied across 2 shared benchmarks. Check the table for category-level strengths. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.

Is GPT-5.1 Codex Mini or Qwen3.5-35B-A3B better for production use?

Both GPT-5.1 Codex Mini and Qwen3.5-35B-A3B are production API models. For cost-sensitive production traffic, GPT-5.1 Codex Mini has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.

Can I switch between GPT-5.1 Codex Mini and Qwen3.5-35B-A3B in my app?

Yes. Call GPT-5.1 Codex Mini through OpenAI and Qwen3.5-35B-A3B through Qwen with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.

How accurate is this GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B pricing data?

List rates are the latest published OpenAI API pricing and Qwen API pricing, quoted per million tokens. Official rate sheets: https://developers.openai.com/api/docs/pricing and https://bailian.console.aliyun.com/. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.

What is the output token limit for GPT-5.1 Codex Mini and Qwen3.5-35B-A3B?

GPT-5.1 Codex Mini supports up to 128K output tokens per request, while Qwen3.5-35B-A3B supports up to 65K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.

Which model has better throughput, GPT-5.1 Codex Mini or Qwen3.5-35B-A3B?

GPT-5.1 Codex Mini has a measured throughput of approximately 200 tokens/second. Throughput data for Qwen3.5-35B-A3B is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.

How do I switch the models in this GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B comparison?

Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open GPT-5.1 Codex Mini or Qwen3.5-35B-A3B from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.

GPT-5.1 Codex Mini vs Qwen3.5-35B-A3B pricing

This comparison covers API pricing, context window, throughput, and benchmark scores. GPT-5.1 Codex Mini costs $0.25/M input and $2.00/M output. Qwen3.5-35B-A3B costs $0.25/M input and $2.00/M output.

Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.