LogoLMSpeed
Back to models

Model compare

Claude Opus 4.6 vs GPT-5.3 Codex

The readout for Claude Opus 4.6 and GPT-5.3 Codex, before the detailed comparison sheet.

Model A

Claude Opus 4.6

Anthropic

Contender
vs

Model B

GPT-5.3 Codex

OpenAI

Leading

Key Takeaways

Weighted outcome: GPT-5.3 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.

Decision read

GPT-5.3 Codex

GPT-5.3 Codex has the higher weighted result; Model A / B score 17.3 to 82.7.

Evidence depth

130 data points

Includes 33 benchmark rows, 0 audit samples, and 10 provider examples.

Selection signal

Start with GPT-5.3 Codex

The charts below split 43 high-signal samples across speed, scores, and audit health.

Change comparison

Switch either side of this report to compare another model with the same LMSpeed data pipeline.

Select a different model to open a new comparison URL.

Comparison sheet

This report only uses LMSpeed data for Claude Opus 4.6 and GPT-5.3 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.

Model compare
Claude Opus 4.6
GPT-5.3 Codex
Overall leaderContenderLeading
Weighted overall score17.3 pts82.7 pts
Benchmark category leads1 categories5 categories
Operational advantagesCheapest input priceAverage speed, First-token latency, Free providers, Provider coverage
Context window1M tokens400K tokens
Max output128K tokens128K tokens
Modalities

Input

TextImageFile

Output

Text

Input

TextImageFile

Output

Text
Features
Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning
Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning

The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.

Model metadata

Model compare
Claude Opus 4.6
GPT-5.3 Codex
DeveloperAnthropicOpenAI
ReleasedFeb 2026Feb 2026
ParametersNo dataNo data
TokenizerClaudeGPT
Knowledge cutoffNo dataNo data
OpenRouter IDanthropic/claude-opus-4.6openai/gpt-5.3-codex
ReferencesNo dataNo data

When to choose each model

This report only uses LMSpeed data for Claude Opus 4.6 and GPT-5.3 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.

Claude Opus 4.6

Claude Opus 4.6 is stronger in benchmark categories (Agents) and operational dimensions (Cheapest input price).

GPT-5.3 Codex

GPT-5.3 Codex is stronger in benchmark categories (Coding, Reasoning, Knowledge, Multimodal, Instruction following) and operational dimensions (Average speed, First-token latency, Free providers, Provider coverage).

Benchmark score comparison

Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.

Category performance

Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.

Model A coverage
8 / 8
Model B coverage
6 / 8
Shared
6 shared categories

Avg. score

Claude Opus 4.6

51.8

Avg. score

GPT-5.3 Codex

55.3

Agents

Claude Opus 4.6 leads by 2.2

Claude Opus 4.654.3
GPT-5.3 Codex52.1

Coding

GPT-5.3 Codex leads by 0.5

Claude Opus 4.656.6
GPT-5.3 Codex57.1

Reasoning

GPT-5.3 Codex leads by 6.4

Claude Opus 4.653.4
GPT-5.3 Codex59.8

Knowledge

GPT-5.3 Codex leads by 3.8

Claude Opus 4.653.3
GPT-5.3 Codex57.1

Math

Claude Opus 4.6

Claude Opus 4.655.7
GPT-5.3 Codex-

Multilingual

Claude Opus 4.6

Claude Opus 4.648.4
GPT-5.3 Codex-

Multimodal

GPT-5.3 Codex leads by 3.0

Claude Opus 4.647.8
GPT-5.3 Codex50.8

Instruction following

GPT-5.3 Codex leads by 9.8

Claude Opus 4.644.8
GPT-5.3 Codex54.6

Professional benchmark details

Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.

Aggregatereported

BenchLM overall score

SourceClaude Opus 4.6

Claude Opus 4.6

62.0

Rank #41/111 · confidence 4 · eval date 2026-02-01

+6.0

GPT-5.3 Codex

winner

68.0

Rank #26/111 · confidence 3 · eval date 2026-02-05

Pricingverified

Input price

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

$5.00/M

Rank #168/186 · confidence 4

+$3.25/M

GPT-5.3 Codex

winner

$1.75/M

Rank #140/186 · confidence 4

Pricingverified

Blended price

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

$10.00/M

Rank #169/186 · confidence 4

+$5.19/M

GPT-5.3 Codex

winner

$4.81/M

Rank #155/186 · confidence 4

Pricingverified

Output price

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

$25.00/M

Rank #169/186 · confidence 4

+$11.00/M

GPT-5.3 Codex

winner

$14.00/M

Rank #156/186 · confidence 4

Reasoningreported

BenchLM Reasoning score

SourceClaude Opus 4.6

Claude Opus 4.6

67.1

Rank #42/67 · confidence 4 · eval date 2026-02-01

+11.2

GPT-5.3 Codex

winner

78.3

Rank #5/67 · confidence 3 · eval date 2026-02-05

Reasoningreported

AA-LCR

SourceClaude Opus 4.6

Claude Opus 4.6

67.0

Rank #71/106 · confidence 4 · eval date 2026-02-01

+16.3

GPT-5.3 Codex

winner

83.3

Rank #6/106 · confidence 3 · eval date 2026-02-05

Reasoningverified

GPQA

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

84.0%

Rank #75/218 · confidence 4

+7.5%

GPT-5.3 Codex

winner

91.5%

Rank #21/218 · confidence 4

Reasoningreported

CritPt

SourceClaude Opus 4.6

Claude Opus 4.6

2.8

Rank #57/88 · confidence 4 · eval date 2026-02-01

+14.1

GPT-5.3 Codex

winner

16.9

Rank #22/88 · confidence 3 · eval date 2026-02-05

Reasoningverified

HLE

SourceClaude Opus 4.6 (Non-reasoning, High Effort)

Claude Opus 4.6

19.1%

Rank #89/216 · confidence 4

+23.4%

GPT-5.3 Codex

winner

42.5%

Rank #22/216 · confidence 4

Codingreported

SWE-Rebench

SourceClaude Opus 4.6

Claude Opus 4.6

winner

65.3

Rank #1/11 · confidence 4 · eval date 2026-02-01

+7.1

GPT-5.3 Codex

58.2

Rank #9/11 · confidence 3 · eval date 2026-02-05

Codingreported

Vibe Code Bench

SourceClaude Opus 4.6

Claude Opus 4.6

57.6

Rank #5/33 · confidence 4 · eval date 2026-02-01

+4.2

GPT-5.3 Codex

winner

61.8

Rank #4/33 · confidence 3 · eval date 2026-02-05

Codingreported

SWE-bench Verified

SourceClaude Opus 4.6

Claude Opus 4.6

80.8

Rank #8/49 · confidence 4 · eval date 2026-02-01

+4.2

GPT-5.3 Codex

winner

85.0

Rank #6/49 · confidence 3 · eval date 2026-02-05

Codingreported

AA-SciCode

SourceClaude Opus 4.6

Claude Opus 4.6

45.7

Rank #54/113 · confidence 4 · eval date 2026-02-01

+7.5

GPT-5.3 Codex

winner

53.2

Rank #26/113 · confidence 3 · eval date 2026-02-05

Codingreported

SWE-bench Pro

SourceClaude Opus 4.6

Claude Opus 4.6

53.4

Rank #41/50 · confidence 4 · eval date 2026-02-01

+3.4

GPT-5.3 Codex

winner

56.8

Rank #26/50 · confidence 3 · eval date 2026-02-05

Codingreported

BenchLM Coding score

SourceClaude Opus 4.6

Claude Opus 4.6

50.3

Rank #54/87 · confidence 4 · eval date 2026-02-01

+1.7

GPT-5.3 Codex

winner

52.0

Rank #50/87 · confidence 3 · eval date 2026-02-05

Knowledgereported

AA-Omniscience Accuracy

SourceClaude Opus 4.6

Claude Opus 4.6

45.8

Rank #23/106 · confidence 4 · eval date 2026-02-01

+7.1

GPT-5.3 Codex

winner

52.9

Rank #11/106 · confidence 3 · eval date 2026-02-05

Knowledgereported

BenchLM Knowledge score

SourceClaude Opus 4.6

Claude Opus 4.6

winner

79.8

Rank #15/83 · confidence 4 · eval date 2026-02-01

+0.3

GPT-5.3 Codex

79.5

Rank #19/83 · confidence 3 · eval date 2026-02-05

Knowledgereported

AA-HLE

SourceClaude Opus 4.6

Claude Opus 4.6

19.1

Rank #74/114 · confidence 4 · eval date 2026-02-01

+23.4

GPT-5.3 Codex

winner

42.5

Rank #21/114 · confidence 3 · eval date 2026-02-05

Knowledgereported

AA-Omniscience Hallucination Rate

SourceClaude Opus 4.6

Claude Opus 4.6

80.1

Rank #43/106 · confidence 4 · eval date 2026-02-01

+9.1

GPT-5.3 Codex

winner

89.2

Rank #21/106 · confidence 3 · eval date 2026-02-05

Knowledgereported

AA-GPQA Diamond

SourceClaude Opus 4.6

Claude Opus 4.6

84.0

Rank #67/113 · confidence 4 · eval date 2026-02-01

+7.5

GPT-5.3 Codex

winner

91.5

Rank #23/113 · confidence 3 · eval date 2026-02-05

Knowledgereported

AA-Omniscience Index

SourceClaude Opus 4.6

Claude Opus 4.6

2.4

Rank #36/45 · confidence 4 · eval date 2026-02-01

+8.5

GPT-5.3 Codex

winner

10.9

Rank #25/45 · confidence 3 · eval date 2026-02-05

Knowledgereported

Artificial Analysis Intelligence Index

SourceClaude Opus 4.6

Claude Opus 4.6

26.4

Rank #57/117 · confidence 4 · eval date 2026-02-01

+6.1

GPT-5.3 Codex

winner

32.5

Rank #43/117 · confidence 3 · eval date 2026-02-05

Multimodalreported

Design Arena Website

SourceClaude Opus 4.6

Claude Opus 4.6

winner

1306.0

Rank #14/78 · confidence 4 · eval date 2026-02-01

+129.0

GPT-5.3 Codex

1177.0

Rank #59/78 · confidence 3 · eval date 2026-02-05

Multimodalreported

BenchLM Multimodal Grounded score

SourceClaude Opus 4.6

Claude Opus 4.6

59.5

Rank #40/56 · confidence 4 · eval date 2026-02-01

+16.1

GPT-5.3 Codex

winner

75.6

Rank #20/56 · confidence 3 · eval date 2026-02-05

Multimodalreported

AA-MMMU-Pro

SourceClaude Opus 4.6

Claude Opus 4.6

72.5

Rank #45/68 · confidence 4 · eval date 2026-02-01

+6.0

GPT-5.3 Codex

winner

78.5

Rank #22/68 · confidence 3 · eval date 2026-02-05

Instruction followingreported

BenchLM Instruction Following score

SourceClaude Opus 4.6

Claude Opus 4.6

52.6

Rank #49/52 · confidence 4 · eval date 2026-02-01

+40.0

GPT-5.3 Codex

winner

92.6

Rank #10/52 · confidence 3 · eval date 2026-02-05

Instruction followingreported

AA-IFBench

SourceClaude Opus 4.6

Claude Opus 4.6

44.6

Rank #59/84 · confidence 4 · eval date 2026-02-01

+30.8

GPT-5.3 Codex

winner

75.4

Rank #18/84 · confidence 3 · eval date 2026-02-05

Agentsreported

JobBench

SourceClaude Opus 4.6

Claude Opus 4.6

winner

36.7

Rank #9/24 · confidence 4 · eval date 2026-02-01

+3.0

GPT-5.3 Codex

33.7

Rank #11/24 · confidence 3 · eval date 2026-02-05

Agentsreported

Gert Labs

SourceClaude Opus 4.6

Claude Opus 4.6

winner

61.9

Rank #10/49 · confidence 4 · eval date 2026-02-01

+4.4

GPT-5.3 Codex

57.5

Rank #13/49 · confidence 3 · eval date 2026-02-05

Agentsreported

Terminal-Bench 2.0

SourceClaude Opus 4.6

Claude Opus 4.6

65.4

Rank #24/53 · confidence 4 · eval date 2026-02-01

+11.9

GPT-5.3 Codex

winner

77.3

Rank #11/53 · confidence 3 · eval date 2026-02-05

Agentsreported

OSWorld-Verified

SourceClaude Opus 4.6

Claude Opus 4.6

winner

72.7

Rank #15/27 · confidence 4 · eval date 2026-02-01

+8.0

GPT-5.3 Codex

64.7

Rank #21/27 · confidence 3 · eval date 2026-02-05

Agentsreported

BenchLM Agentic score

SourceClaude Opus 4.6

Claude Opus 4.6

winner

63.5

Rank #36/76 · confidence 4 · eval date 2026-02-01

+0.7

GPT-5.3 Codex

62.8

Rank #37/76 · confidence 3 · eval date 2026-02-05

Agentsreported

τ²-bench results

SourceClaude Opus 4.6

Claude Opus 4.6

84.8

Rank #46/82 · confidence 4 · eval date 2026-02-01

+1.2

GPT-5.3 Codex

winner

86.0

Rank #42/82 · confidence 3 · eval date 2026-02-05

API audit comparison

Latest completed audits from shared providers, with four safety and integrity score groups plus report links.

Provider
Claude Opus 4.6
GPT-5.3 Codex
No completed audits are available from shared providers yet.

Provider examples

Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.

Provider
Claude Opus 4.6
GPT-5.3 Codex
UoCode30 tests

Claude Opus 4.6

speed / latency

38 tok/s / 2611ms

input / output

No data

GPT-5.3 Codex

speed / latency

56 tok/s / 4621ms

input / output

No data

钠 API25 tests

Claude Opus 4.6

speed / latency

42 tok/s / 2282ms

input / output

No data

GPT-5.3 Codex

speed / latency

63 tok/s / 3786ms

input / output

No data

Kunkunout API20 tests

Claude Opus 4.6

speed / latency

40 tok/s / 16141ms

input / output

No data

GPT-5.3 Codex

speed / latency

N/A / N/A

input / output

No data

Rnglg2 API15 tests

Claude Opus 4.6

speed / latency

57 tok/s / 3926ms

input / output

No data

GPT-5.3 Codex

speed / latency

N/A / N/A

input / output

No data

小水管 API15 tests

Claude Opus 4.6

speed / latency

45 tok/s / 6167ms

input / output

No data

GPT-5.3 Codex

speed / latency

201 tok/s / 2135ms

input / output

No data

兔子API

Claude Opus 4.6

claude-opus-4-6-low

speed / latency

No data

input / output

$0/request

GPT-5.3 Codex

gpt-5.3-codex

speed / latency

No data

input / output

$0/request

KFCV50

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.017/request

GPT-5.3 Codex

gpt-5.3-codex-medium

speed / latency

No data

input / output

$0.0068/request

VSLLM

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.365/request

GPT-5.3 Codex

gpt-5.3-codex-spark

speed / latency

No data

input / output

$0.0073/request

Jeniya AI API

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.131/M/$0.654/M

GPT-5.3 Codex

gpt-5.3-codex-spark

speed / latency

No data

input / output

$0.019/M/$0.153/M

N1N

Claude Opus 4.6

claude-opus-4-6

speed / latency

No data

input / output

$0.131/M/$0.654/M

GPT-5.3 Codex

gpt-5.3-codex-spark

speed / latency

No data

input / output

$0.019/M/$0.153/M

FAQ

Weighted outcome: GPT-5.3 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.

Why is this comparison indexable?
It has 6 verifiable comparison points, and both models have pricing or benchmark data.
Are missing metrics invented?
No. Metrics without LMSpeed data are omitted from this report.

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.