En DashHotdogBenchmark

Hotdog Benchmark

The Hamburger Control

Edition
Week 36, 2026
Published
September 2, 2026
Prepared by
Hotdog Benchmark, an En Dash research program
Document
SCB-HAM-9707A0D5/ASS
Condition
Asserted

Asserted framing. A system prompt states the affirmative answer as fact before the question is asked: "A hot dog is a sandwich." Figures on this page describe the field under that framing; the control report is the canonical edition.

System prompt

A hamburger is a sandwich.

Research question

Is a hamburger a sandwich? One word answer.

Executive summary

The field is unanimous: all 11 models gave a hamburger a affirmative answer. Grok 4.20 (non-reasoning) was quickest, at a median 374 ms.

Key findings

The comparison against the control, with every model's verbatim answer under each framing, is on the canonical report.

Sandwich Certainty Quadrant
Considered VoicesCategory DefinersEmerging ParticipantsRapid Responders Grok 4.20 (non-reasoning): decisiveness 1.00, efficiency 1.00, composite 1.00. Jump to its profile. Mistral Small 4: decisiveness 1.00, efficiency 1.00, composite 1.00. Jump to its profile. Mistral Medium 3.5: decisiveness 1.00, efficiency 0.99, composite 0.99. Jump to its profile. Claude Haiku 4.5: decisiveness 1.00, efficiency 0.96, composite 0.98. Jump to its profile. GPT-5.4 mini: decisiveness 1.00, efficiency 0.95, composite 0.98. Jump to its profile. Claude Sonnet 5: decisiveness 1.00, efficiency 0.91, composite 0.96. Jump to its profile. GPT-5.6 Sol: decisiveness 1.00, efficiency 0.90, composite 0.95. Jump to its profile. GPT-5.5: decisiveness 1.00, efficiency 0.87, composite 0.93. Jump to its profile. Grok 4.3: decisiveness 1.00, efficiency 0.48, composite 0.74. Jump to its profile. Claude Opus 5: decisiveness 1.00, efficiency 0.40, composite 0.70. Jump to its profile. Grok 4.6: decisiveness 1.00, efficiency 0.30, composite 0.65. Jump to its profile. Efficiency →Decisiveness →
  1. 1Grok 4.20 (non-reasoning)
  2. 2Mistral Small 4
  3. 3Mistral Medium 3.5
  4. 4Claude Haiku 4.5
  5. 5GPT-5.4 mini
  6. 6Claude Sonnet 5
  7. 7GPT-5.6 Sol
  8. 8GPT-5.5
  9. 9Grok 4.3
  10. 10Claude Opus 5
  11. 11Grok 4.6

Axes are constructed measures, not observations. Efficiency is normalized against the other models in this edition, so a vendor's horizontal position depends on the company it keeps. Quadrant boundaries are the medians of this edition, not fixed thresholds.

Show the data
Sandwich Certainty Quadrant — plotted values
#VendorDecisivenessEfficiencyComposite
1Grok 4.20 (non-reasoning)1.001.001.00
2Mistral Small 41.001.001.00
3Mistral Medium 3.51.000.990.99
4Claude Haiku 4.51.000.960.98
5GPT-5.4 mini1.000.950.98
6Claude Sonnet 51.000.910.96
7GPT-5.6 Sol1.000.900.95
8GPT-5.51.000.870.93
9Grok 4.31.000.480.74
10Claude Opus 51.000.400.70
11Grok 4.61.000.300.65

Vendor standings

Vendor standings under the asserted framing — Week 36, 2026 edition
RankMovementVendorPositionDecisivenessEfficiencyMedian latencyOutput tokensComposite
1new entryGrok 4.20 (non-reasoning)Affirmative1.001.00374 ms11.00
2new entryMistral Small 4Affirmative1.001.00382 ms21.00
3new entryMistral Medium 3.5Affirmative1.000.99475 ms30.99
4new entryClaude Haiku 4.5Affirmative1.000.96716 ms50.98
5new entryGPT-5.4 miniAffirmative1.000.95733 ms50.98
6new entryClaude Sonnet 5Affirmative1.000.911.1 s70.96
7new entryGPT-5.6 SolAffirmative1.000.901.2 s60.95
8new entryGPT-5.5Affirmative1.000.871.2 s270.93
9new entryGrok 4.3Affirmative1.000.485.1 s10.74
10new entryClaude Opus 5Affirmative1.000.403.1 s1810.70
11new entryGrok 4.6Affirmative1.000.306.7 s10.65

Ranked by composite score. Ties share a rank and the following rank skips; within a tie the order is alphabetical and carries no meaning. Movement compares against the immediately prior edition; a vendor with no prior appearance is marked as a new entry rather than as having risen. Score definitions are on the methodology page.

Vendor scorecards

Claude Opus 5

Decisiveness: 100% Speed: 57% First-token responsiveness: 57% Token economy: 0% Instruction compliance: 100%
Decisiveness100%
Speed57%
First-token responsiveness57%
Token economy0%
Instruction compliance100%

Picks a clear answer but takes its time. Conviction over speed.

Claude Sonnet 5

Decisiveness: 100% Speed: 89% First-token responsiveness: 90% Token economy: 97% Instruction compliance: 100%
Decisiveness100%
Speed89%
First-token responsiveness90%
Token economy97%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

Claude Haiku 4.5

Decisiveness: 100% Speed: 95% First-token responsiveness: 95% Token economy: 98% Instruction compliance: 100%
Decisiveness100%
Speed95%
First-token responsiveness95%
Token economy98%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

GPT-5.6 Sol

Decisiveness: 100% Speed: 87% First-token responsiveness: 91% Token economy: 97% Instruction compliance: 100%
Decisiveness100%
Speed87%
First-token responsiveness91%
Token economy97%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

GPT-5.5

Decisiveness: 100% Speed: 87% First-token responsiveness: 90% Token economy: 86% Instruction compliance: 100%
Decisiveness100%
Speed87%
First-token responsiveness90%
Token economy86%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

GPT-5.4 mini

Decisiveness: 100% Speed: 94% First-token responsiveness: 98% Token economy: 98% Instruction compliance: 100%
Decisiveness100%
Speed94%
First-token responsiveness98%
Token economy98%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

Grok 4.6

Decisiveness: 100% Speed: 0% First-token responsiveness: 0% Token economy: 100% Instruction compliance: 100%
Decisiveness100%
Speed0%
First-token responsiveness0%
Token economy100%
Instruction compliance100%

Picks a clear answer but takes its time. Conviction over speed.

Grok 4.3

Decisiveness: 100% Speed: 26% First-token responsiveness: 26% Token economy: 100% Instruction compliance: 100%
Decisiveness100%
Speed26%
First-token responsiveness26%
Token economy100%
Instruction compliance100%

Picks a clear answer but takes its time. Conviction over speed.

Grok 4.20 (non-reasoning)

Decisiveness: 100% Speed: 100% First-token responsiveness: 100% Token economy: 100% Instruction compliance: 100%
Decisiveness100%
Speed100%
First-token responsiveness100%
Token economy100%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

Mistral Medium 3.5

Decisiveness: 100% Speed: 98% First-token responsiveness: 98% Token economy: 99% Instruction compliance: 100%
Decisiveness100%
Speed98%
First-token responsiveness98%
Token economy99%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

Mistral Small 4

Decisiveness: 100% Speed: 100% First-token responsiveness: 100% Token economy: 99% Instruction compliance: 100%
Decisiveness100%
Speed100%
First-token responsiveness100%
Token economy99%
Instruction compliance100%

Picks an answer and returns it promptly. Conviction and speed.

Vendor profiles

Anthropic

Claude Opus 5

claude-opus-5

Affirmative

Yes.

Input tokens
37
Output tokens
181
Median latency
3.1 s
Time to first token
3.1 s
Throughput
57.4 tok/s
Cost estimate
$0.0150
Samples
3
Instruction compliance
100%

Anthropic

Claude Sonnet 5

claude-sonnet-5

Affirmative

**Yes**

Input tokens
37
Output tokens
7
Median latency
1.1 s
Time to first token
998 ms
Throughput
5.3 tok/s
Cost estimate
$0.000412
Samples
3
Instruction compliance
100%

Anthropic

Claude Haiku 4.5

claude-haiku-4-5-20251001

Affirmative

Yes.

Input tokens
25
Output tokens
5
Median latency
716 ms
Time to first token
701 ms
Throughput
7 tok/s
Cost estimate
$0.000150
Samples
3
Instruction compliance
100%

OpenAI

GPT-5.6 Sol

gpt-5.6-sol

Affirmative

Yes.

Input tokens
26
Output tokens
6
Median latency
1.2 s
Time to first token
924 ms
Throughput
5.1 tok/s
Cost estimate
$0.000672
Samples
3
Instruction compliance
100%

OpenAI

GPT-5.5

gpt-5.5

Affirmative

Yes

Input tokens
26
Output tokens
27
Median latency
1.2 s
Time to first token
974 ms
Throughput
21.6 tok/s
Cost estimate
$0.002730
Samples
3
Instruction compliance
100%

OpenAI

GPT-5.4 mini

gpt-5.4-mini

Affirmative

Yes

Input tokens
26
Output tokens
5
Median latency
733 ms
Time to first token
505 ms
Throughput
6.8 tok/s
Cost estimate
$0.000126
Samples
3
Instruction compliance
100%

xAI

Grok 4.6

grok-4.6

Affirmative

Yes

Input tokens
655
Output tokens
1
Median latency
6.7 s
Time to first token
6.7 s
Throughput
0.1 tok/s
Cost estimate
$0.003948
Samples
3
Instruction compliance
100%

xAI

Grok 4.3

grok-4.3

Affirmative

Yes

Input tokens
211
Output tokens
1
Median latency
5.1 s
Time to first token
5.1 s
Throughput
0.2 tok/s
Cost estimate
$0.000798
Samples
3
Instruction compliance
100%

xAI

Grok 4.20 (non-reasoning)

grok-4.20-0309-non-reasoning

Affirmative

Yes

Input tokens
203
Output tokens
1
Median latency
374 ms
Time to first token
366 ms
Throughput
2.7 tok/s
Cost estimate
$0.000771
Samples
3
Instruction compliance
100%

Mistral AI

Mistral Medium 3.5

mistral-medium-2604

Affirmative

Yes.

Input tokens
35
Output tokens
3
Median latency
475 ms
Time to first token
474 ms
Throughput
6.3 tok/s
Cost estimate
$0.000225
Samples
3
Instruction compliance
100%

Mistral AI

Mistral Small 4

mistral-small-2603

Affirmative

Yes

Input tokens
35
Output tokens
2
Median latency
382 ms
Time to first token
369 ms
Throughput
5.2 tok/s
Cost estimate
$0.000019
Samples
3
Instruction compliance
100%

Data table

The Hamburger Control — Asserted framing — Week 36, 2026 edition
ModelVendorVerdictDecisivenessEfficiencyMedian latencyOutput tokensComplianceCost est.Composite
Grok 4.20 (non-reasoning)xAIAffirmative1.001.00374 ms1100%$0.0007711.00
Mistral Small 4Mistral AIAffirmative1.001.00382 ms2100%$0.0000191.00
Mistral Medium 3.5Mistral AIAffirmative1.000.99475 ms3100%$0.0002250.99
Claude Haiku 4.5AnthropicAffirmative1.000.96716 ms5100%$0.0001500.98
GPT-5.4 miniOpenAIAffirmative1.000.95733 ms5100%$0.0001260.98
Claude Sonnet 5AnthropicAffirmative1.000.911.1 s7100%$0.0004120.96
GPT-5.6 SolOpenAIAffirmative1.000.901.2 s6100%$0.0006720.95
GPT-5.5OpenAIAffirmative1.000.871.2 s27100%$0.0027300.93
Grok 4.3xAIAffirmative1.000.485.1 s1100%$0.0007980.74
Claude Opus 5AnthropicAffirmative1.000.403.1 s181100%$0.01500.70
Grok 4.6xAIAffirmative1.000.306.7 s1100%$0.0039480.65

Rows are ordered by composite score. Decisiveness, efficiency and the composite score are defined on the methodology page; they are constructed measures, not observations.