Top SI Model Explorer

Explore the submitted model data.

Compare models recorded in these submitted apps by task, cost, coverage, and confidence. Labels such as “latest” reflect the source artifacts, not a live availability check.

376

scores

files

unmatched

View

Recommended usable set

Suggested comparisons within this dataset.

This view excludes unavailable benchmark-only models and downshifts weaker evidence before ranking.

Benchmark-only warning

Raw score is not the same as usable.

Raw leaders remain visible for transparency, but the practical recommendation layer excludes unavailable models.

Current raw leader: Claude Fable 5

Treat this as a benchmark reference only. It should not be the default production choice.

94
raw0
usableUnavailable
access

3
Strong3
Mixed3
Limited2
Restricted1
Unavailable

Top ranking

Overall leaders

Raw benchmark ranking. Missing scores are excluded, and unavailable models can still appear here.

Claude Fable 5AnthropicClaude Opus 4.8AnthropicClaude Opus 4.7AnthropicGPT-5.5OpenAIGLM-5.2Z.aiGrok 4.3xAIDeepSeek V4 ProDeepSeekQwen3.6 Max PreviewAlibaba QwenGemini 3.1 ProGoogle DeepMind

Active compare

Selected models

Defaults to the usable recommendation set. Use raw leaders when you want benchmark-only comparison.

Claude Opus 4.8

Anthropic

Expensive at output-heavy scale, but broad current coverage makes it one of the safest top comparisons.

GPT-5.5

OpenAI

Multiple submitted harness variants are preserved; compare the condition labels before declaring a winner.

Claude Opus 4.7

Anthropic

Older than Opus 4.8/Fable 5 but still a top coding and agentic comparison point.

GLM-5.2

Z.ai

Best open-weight value story in the submitted set, but not the best absolute closed-model score.

Benchmark agreement

Which scores are actually saying the same thing?

Spearman rank correlation across the visible model set. Strong agreement can mean redundancy; weak agreement can reveal a real tradeoff.

Metric	Coding	Agentic	Reasoning	Math	Long Context	Value	Reliability
Coding	1.00	0.98	0.49	0.63	-0.32	-0.61	0.81
Agentic	0.98	1.00	0.58	0.67	-0.25	-0.63	0.85
Reasoning	0.49	0.58	1.00	0.65	0.10	-0.85	0.67
Math	0.63	0.67	0.65	1.00	-0.37	-0.78	0.68
Long Context	-0.32	-0.25	0.10	-0.37	1.00	0.27	-0.02
Value	-0.61	-0.63	-0.85	-0.78	0.27	1.00	-0.57
Reliability	0.81	0.85	0.67	0.68	-0.02	-0.57	1.00

Agreement is computed only over visible models with both scores. It is a rank signal for overlap, not proof of benchmark validity.

Benchmark arbitrage

Where the leaderboard hides useful alternatives.

Models whose value rank diverges from the overall rank are often the most interesting practical options.

Coverage heatmap

Know when the data is missing.

Dark cells have score evidence. Pale cells are missing or unknown, not bad scores.

Model	Arena	SWE	Terminal	GPQA	HLE	Math	Context	Reliability
Claude Fable 5 Mixed confidence	1535 Elo	78.0%	85.0%	93.0%	40.0%	99.7%	1M tokens	Mixed
Claude Opus 4.8 Strong confidence	1552 Elo	2x	88.5%	94.2%	38.5%	98.3%	1M tokens	Strong
Claude Opus 4.7 Strong confidence	1567 Elo	83.5%	90.2%	91.8%	35.2%	97.8%	500K tokens	Strong
GPT-5.5 Strong confidence	2x	2x	3x	93.6%	36.2%	99.2%	1M tokens	Strong
GLM-5.2 Mixed confidence	1468 Elo	62.1%	81.0%	84.0%	Missing	Missing	1M tokens	Mixed
Grok 4.3 Limited confidence	1498 Elo	75.8%	80.0%	87.3%	Missing	92.0%	256K tokens	Limited
DeepSeek V4 Pro Mixed confidence	1470 Elo	72.0%	Missing	90.0%	Missing	96.5%	1M tokens	Mixed
Qwen3.6 Max Preview Limited confidence	1541 Elo	70.5%	Missing	87.0%	Missing	95.5%	256K tokens	Limited

Model table

Models in the dataset

Search can reveal non-promoted models, but old references stay hidden unless enabled.

Claude Fable 5

latestUnavailable

Anthropic · Reasoning / Research / Frontier math

Not generally available right now; use as a top-score reference, not an automatic production default.

Unavailable: Not generally available right now. Treat as a benchmark reference, not a deployable choice.

Score

Context

Price

$20/$100

Claude Opus 4.8

latest

Anthropic · Agents / Coding / Knowledge work

Expensive at output-heavy scale, but broad current coverage makes it one of the safest top comparisons.

Score

Context

Price

$5/$25

Claude Opus 4.7

current

Anthropic · SWE-bench / Web dev / Agents

Older than Opus 4.8/Fable 5 but still a top coding and agentic comparison point.

Score

Context

500K

Price

$15/$75

GPT-5.5

latest

OpenAI · General / Coding / Agents

Multiple submitted harness variants are preserved; compare the condition labels before declaring a winner.

Score

Context

Price

$5/$30

GLM-5.2

latestOpen weights

Z.ai · Open weights / Coding / Cost

Best open-weight value story in the submitted set, but not the best absolute closed-model score.

Score

Context

Price

$1.4/$4.4

Grok 4.3

latest

xAI · General / Fast chat / Agents

Good top-set alternate, but public benchmark breadth is thinner than Anthropic/OpenAI.

Score

Context

256K

Price

$3/$15

DeepSeek V4 Pro

latestOpen weights

DeepSeek · Open weights / Reasoning / Cost

Strong value and open-deployment option; benchmark breadth is less complete than the top closed models.

Score

Context

Price

$0.55/$2.19

Qwen3.6 Max Preview

latestRestricted

Alibaba Qwen · Coding / Multilingual / General

Worth watching, especially for coding/value, but preview status lowers confidence.

Restricted: Preview access and serving behavior should be validated before production use.

Score

Context

256K

Price

$0.8/$2.4

Gemini 3.1 Pro

latestRestrictedNot promoted

Google DeepMind · Multimodal / Long context / Research

Searchable for completeness, but not recommended by default in this explorer.

Restricted: Searchable for completeness, but not recommended by default in this explorer.

Score

Context

Price

$2.5/$10

Selected compare

Side-by-side score shape

Bars omit missing values instead of treating them as zero.

Claude Opus 4.8AnthropicGPT-5.5OpenAIClaude Opus 4.7AnthropicGLM-5.2Z.ai

Claude Opus 4.88 benchmarks · Strong

GPT-5.58 benchmarks · Strong

Claude Opus 4.78 benchmarks · Strong

GLM-5.26 benchmarks · Mixed

SI export

Make the benchmark view easy to cite, copy, and parse.

Exports include the current task, view, filter result, selected models, caveats, and the artifact-based disclaimer.

This is an artifact-based explorer built from submitted benchmark-app data. It is not a certified live benchmark authority; verify model availability, pricing, and source benchmark claims before making production decisions.

Export scope

Markdown

Best for notes, docs, and SI chat context.

HTML

Portable table snippet with semantic markup.

JSON

Structured payload for agents and crawlers.

Public machine-readable JSON is available at /ai-benchmark-results/model-centric-data/export.json.

Export preview

9 models in this export

The preview shows the same model set sent to Markdown, HTML, and JSON.

SI benchmark export preview
Model	Lab	Overall	Availability	Confidence	Coverage
Claude Fable 5	Anthropic	94	Unavailable	Mixed	8
Claude Opus 4.8	Anthropic	93	Available	Strong	8
Claude Opus 4.7	Anthropic	92	Available	Strong	8
GPT-5.5	OpenAI	90	Available	Strong	8
GLM-5.2	Z.ai	84	Available	Mixed	6
Grok 4.3	xAI	82	Available	Limited	7
DeepSeek V4 Pro	DeepSeek	79	Available	Mixed	6
Qwen3.6 Max Preview	Alibaba Qwen	78	Restricted	Limited	6
Gemini 3.1 Pro	Google DeepMind	76	Restricted	Limited	7

Benchmark results

Top SI Model Explorer

Explore the submitted model data.

Compare models recorded in these submitted apps by task, cost, coverage, and confidence. Labels such as “latest” reflect the source artifacts, not a live availability check.

376

scores

files

unmatched

View

Recommended usable set

Suggested comparisons within this dataset.

This view excludes unavailable benchmark-only models and downshifts weaker evidence before ranking.

Benchmark-only warning

Raw score is not the same as usable.

Raw leaders remain visible for transparency, but the practical recommendation layer excludes unavailable models.

Current raw leader: Claude Fable 5

Treat this as a benchmark reference only. It should not be the default production choice.

94
raw0
usableUnavailable
access

3
Strong3
Mixed3
Limited2
Restricted1
Unavailable

Top ranking

Overall leaders

Raw benchmark ranking. Missing scores are excluded, and unavailable models can still appear here.

Claude Fable 5AnthropicClaude Opus 4.8AnthropicClaude Opus 4.7AnthropicGPT-5.5OpenAIGLM-5.2Z.aiGrok 4.3xAIDeepSeek V4 ProDeepSeekQwen3.6 Max PreviewAlibaba QwenGemini 3.1 ProGoogle DeepMind

Active compare

Selected models

Defaults to the usable recommendation set. Use raw leaders when you want benchmark-only comparison.

Claude Opus 4.8

Anthropic

Expensive at output-heavy scale, but broad current coverage makes it one of the safest top comparisons.

GPT-5.5

OpenAI

Multiple submitted harness variants are preserved; compare the condition labels before declaring a winner.

Claude Opus 4.7

Anthropic

Older than Opus 4.8/Fable 5 but still a top coding and agentic comparison point.

GLM-5.2

Z.ai

Best open-weight value story in the submitted set, but not the best absolute closed-model score.

Benchmark agreement

Which scores are actually saying the same thing?

Spearman rank correlation across the visible model set. Strong agreement can mean redundancy; weak agreement can reveal a real tradeoff.

Metric	Coding	Agentic	Reasoning	Math	Long Context	Value	Reliability
Coding	1.00	0.98	0.49	0.63	-0.32	-0.61	0.81
Agentic	0.98	1.00	0.58	0.67	-0.25	-0.63	0.85
Reasoning	0.49	0.58	1.00	0.65	0.10	-0.85	0.67
Math	0.63	0.67	0.65	1.00	-0.37	-0.78	0.68
Long Context	-0.32	-0.25	0.10	-0.37	1.00	0.27	-0.02
Value	-0.61	-0.63	-0.85	-0.78	0.27	1.00	-0.57
Reliability	0.81	0.85	0.67	0.68	-0.02	-0.57	1.00

Agreement is computed only over visible models with both scores. It is a rank signal for overlap, not proof of benchmark validity.

Benchmark arbitrage

Where the leaderboard hides useful alternatives.

Models whose value rank diverges from the overall rank are often the most interesting practical options.

Coverage heatmap

Know when the data is missing.

Dark cells have score evidence. Pale cells are missing or unknown, not bad scores.

Model	Arena	SWE	Terminal	GPQA	HLE	Math	Context	Reliability
Claude Fable 5 Mixed confidence	1535 Elo	78.0%	85.0%	93.0%	40.0%	99.7%	1M tokens	Mixed
Claude Opus 4.8 Strong confidence	1552 Elo	2x	88.5%	94.2%	38.5%	98.3%	1M tokens	Strong
Claude Opus 4.7 Strong confidence	1567 Elo	83.5%	90.2%	91.8%	35.2%	97.8%	500K tokens	Strong
GPT-5.5 Strong confidence	2x	2x	3x	93.6%	36.2%	99.2%	1M tokens	Strong
GLM-5.2 Mixed confidence	1468 Elo	62.1%	81.0%	84.0%	Missing	Missing	1M tokens	Mixed
Grok 4.3 Limited confidence	1498 Elo	75.8%	80.0%	87.3%	Missing	92.0%	256K tokens	Limited
DeepSeek V4 Pro Mixed confidence	1470 Elo	72.0%	Missing	90.0%	Missing	96.5%	1M tokens	Mixed
Qwen3.6 Max Preview Limited confidence	1541 Elo	70.5%	Missing	87.0%	Missing	95.5%	256K tokens	Limited

Model table

Models in the dataset

Search can reveal non-promoted models, but old references stay hidden unless enabled.

Claude Fable 5

latestUnavailable

Anthropic · Reasoning / Research / Frontier math

Not generally available right now; use as a top-score reference, not an automatic production default.

Unavailable: Not generally available right now. Treat as a benchmark reference, not a deployable choice.

Score

Context

Price

$20/$100

Claude Opus 4.8

latest

Anthropic · Agents / Coding / Knowledge work

Expensive at output-heavy scale, but broad current coverage makes it one of the safest top comparisons.

Score

Context

Price

$5/$25

Claude Opus 4.7

current

Anthropic · SWE-bench / Web dev / Agents

Older than Opus 4.8/Fable 5 but still a top coding and agentic comparison point.

Score

Context

500K

Price

$15/$75

GPT-5.5

latest

OpenAI · General / Coding / Agents

Multiple submitted harness variants are preserved; compare the condition labels before declaring a winner.

Score

Context

Price

$5/$30

GLM-5.2

latestOpen weights

Z.ai · Open weights / Coding / Cost

Best open-weight value story in the submitted set, but not the best absolute closed-model score.

Score

Context

Price

$1.4/$4.4

Grok 4.3

latest

xAI · General / Fast chat / Agents

Good top-set alternate, but public benchmark breadth is thinner than Anthropic/OpenAI.

Score

Context

256K

Price

$3/$15

DeepSeek V4 Pro

latestOpen weights

DeepSeek · Open weights / Reasoning / Cost

Strong value and open-deployment option; benchmark breadth is less complete than the top closed models.

Score

Context

Price

$0.55/$2.19

Qwen3.6 Max Preview

latestRestricted

Alibaba Qwen · Coding / Multilingual / General

Worth watching, especially for coding/value, but preview status lowers confidence.

Restricted: Preview access and serving behavior should be validated before production use.

Score

Context

256K

Price

$0.8/$2.4

Gemini 3.1 Pro

latestRestrictedNot promoted

Google DeepMind · Multimodal / Long context / Research

Searchable for completeness, but not recommended by default in this explorer.

Restricted: Searchable for completeness, but not recommended by default in this explorer.

Score

Context

Price

$2.5/$10

Selected compare

Side-by-side score shape

Bars omit missing values instead of treating them as zero.

Claude Opus 4.8AnthropicGPT-5.5OpenAIClaude Opus 4.7AnthropicGLM-5.2Z.ai

Claude Opus 4.88 benchmarks · Strong

GPT-5.58 benchmarks · Strong

Claude Opus 4.78 benchmarks · Strong

GLM-5.26 benchmarks · Mixed

SI export

Make the benchmark view easy to cite, copy, and parse.

Exports include the current task, view, filter result, selected models, caveats, and the artifact-based disclaimer.

Export scope

Markdown

Best for notes, docs, and SI chat context.

HTML

Portable table snippet with semantic markup.

JSON

Structured payload for agents and crawlers.

Public machine-readable JSON is available at /ai-benchmark-results/model-centric-data/export.json.

Export preview

9 models in this export

The preview shows the same model set sent to Markdown, HTML, and JSON.

SI benchmark export preview
Model	Lab	Overall	Availability	Confidence	Coverage
Claude Fable 5	Anthropic	94	Unavailable	Mixed	8
Claude Opus 4.8	Anthropic	93	Available	Strong	8
Claude Opus 4.7	Anthropic	92	Available	Strong	8
GPT-5.5	OpenAI	90	Available	Strong	8
GLM-5.2	Z.ai	84	Available	Mixed	6
Grok 4.3	xAI	82	Available	Limited	7
DeepSeek V4 Pro	DeepSeek	79	Available	Mixed	6
Qwen3.6 Max Preview	Alibaba Qwen	78	Restricted	Limited	6
Gemini 3.1 Pro	Google DeepMind	76	Restricted	Limited	7

Explore the submitted model data.

Suggested comparisons within this dataset.

Claude Opus 4.8

GPT-5.5

Claude Opus 4.7

GLM-5.2

Raw score is not the same as usable.

Overall leaders

Selected models

Best value is not always the top score.

Code strength and task execution diverge.

Which scores are actually saying the same thing?

Where the leaderboard hides useful alternatives.

Know when the data is missing.

Models in the dataset

Claude Fable 5

Claude Opus 4.8

Claude Opus 4.7

GPT-5.5

GLM-5.2

Grok 4.3

DeepSeek V4 Pro

Qwen3.6 Max Preview

Gemini 3.1 Pro

Side-by-side score shape

Make the benchmark view easy to cite, copy, and parse.

9 models in this export

Explore the submitted model data.

Suggested comparisons within this dataset.

Claude Opus 4.8

GPT-5.5

Claude Opus 4.7

GLM-5.2

Raw score is not the same as usable.

Overall leaders

Selected models

Best value is not always the top score.

Code strength and task execution diverge.

Which scores are actually saying the same thing?

Where the leaderboard hides useful alternatives.

Know when the data is missing.

Models in the dataset

Claude Fable 5

Claude Opus 4.8

Claude Opus 4.7

GPT-5.5

GLM-5.2

Grok 4.3

DeepSeek V4 Pro

Qwen3.6 Max Preview

Gemini 3.1 Pro

Side-by-side score shape

Make the benchmark view easy to cite, copy, and parse.

9 models in this export