Cost efficiency 1.0

Models: 17
Guesser cost range: 59×
Pareto-efficient: 6 of 17
Most efficient: gpt-oss-120B (high)

Official efficiency ranking

Distance from the lower-left ideal.

Question score and Guesser cost are each scaled from 0 (best among these models) to 1 (worst). The ranking weights both equally and measures the distance from the best possible point. Lower is better.

Distance on the shared scale · lower is betterSelect a model row to view its results

Trade-off map

Cost and question score on a shared scale.

Both axes use the same 0-to-1 scale. Dashed curves connect points at equal distance from the lower-left corner.

Diamond Pareto-efficient: no other model is both cheaper and better Circle Other ranked model

Lower-left is betterCurves show equal ideal distance. Numbers match the table rank.

1. gpt-oss-120B (high)0.096 distance · Pareto-efficient
2. Claude Opus 5 (high)0.127 distance · Pareto-efficient
3. Gemini 3.7 Flash (high)0.151 distance
4. Claude Sonnet 5 (high)0.157 distance
5. Grok 4.6 (high)0.160 distance
6. Grok 4.5 (high)0.160 distance · Pareto-efficient
7. GPT-5 Nano (medium)0.170 distance · Pareto-efficient
8. Gemini 3.8 Flash (high)0.218 distance
9. GPT-5.6 Luna (high)0.283 distance
10. Claude Fable 5 (high)0.343 distance · Pareto-efficient
11. GPT-5.6 Sol (high)0.350 distance
12. Kimi K3 (high)0.396 distance
13. Gemini 3.6 Flash (high)0.407 distance
14. GPT-6 Astra (high)0.665 distance
15. Mistral Medium 3.5 (high)0.908 distance
16. Llama 4 Maverick (non-thinking)1.000 distance · Pareto-efficient
17. Claude Fable 5.1 (high)1.000 distance

Efficiency ranking
Ideal-distance rank			Paretoefficient
Rank 1	gpt-oss-120B (high)cerebras	0.096	Yes	6	13.63	$0.0363	94%
Rank 2	Claude Opus 5 (high)anthropic	0.127	Yes	3	12.34	$0.0705	100%
Rank 3	Gemini 3.7 Flash (high)google-ai-studio	0.151		7	14.03	$0.0653	97%
Rank 4	Claude Sonnet 5 (high)anthropic	0.157		10	14.74	$0.0493	100%
Rank 5	Grok 4.6 (high)xai	0.160		8	14.29	$0.0653	100%
Rank 6	Grok 4.5 (high)xai	0.160	Yes	12	15.17	$0.0286	94%
Rank 7	GPT-5 Nano (medium)openai	0.170	Yes	13	15.49	$0.0138	94%
Rank 8	Gemini 3.8 Flash (high)google-ai-studio	0.218		5	13.14	$0.1128	100%
Rank 9	GPT-5.6 Luna (high)openai	0.283		16	17.74	$0.0184	91%
Rank 10	Claude Fable 5 (high)anthropic	0.343	Yes	1	12.06	$0.1776	100%
Rank 11	GPT-5.6 Sol (high)openai	0.350		9	14.40	$0.1711	100%
Rank 12	Kimi K3 (high)moonshotai	0.396		4	12.74	$0.2032	94%
Rank 13	Gemini 3.6 Flash (high)google-vertex	0.407		14	16.89	$0.1705	97%
Rank 14	GPT-6 Astra (high)openai	0.665		11	15.09	$0.3279	94%
Rank 15	Mistral Medium 3.5 (high)mistral	0.908		17	20.06	$0.4113	89%
Rank 16	Llama 4 Maverick (non-thinking)parasail	1.000	Yes	18	32.23	$0.0086	49%
Rank 17	Claude Fable 5.1 (high)anthropic	1.000		2	12.11	$0.5014	97%

gpt-oss-120B (high)cerebras0.096Ideal distance

Pareto-efficient: Yes
Question score: 13.63
Guesser cost / round: $0.0363

Claude Opus 5 (high)anthropic0.127Ideal distance

Pareto-efficient: Yes
Question score: 12.34
Guesser cost / round: $0.0705

Gemini 3.7 Flash (high)google-ai-studio0.151Ideal distance

Pareto-efficient: No
Question score: 14.03
Guesser cost / round: $0.0653

Claude Sonnet 5 (high)anthropic0.157Ideal distance

Pareto-efficient: No
Question score: 14.74
Guesser cost / round: $0.0493

Grok 4.6 (high)xai0.160Ideal distance

Pareto-efficient: No
Question score: 14.29
Guesser cost / round: $0.0653

Grok 4.5 (high)xai0.160Ideal distance

Pareto-efficient: Yes
Question score: 15.17
Guesser cost / round: $0.0286

GPT-5 Nano (medium)openai0.170Ideal distance

Pareto-efficient: Yes
Question score: 15.49
Guesser cost / round: $0.0138

Gemini 3.8 Flash (high)google-ai-studio0.218Ideal distance

Pareto-efficient: No
Question score: 13.14
Guesser cost / round: $0.1128

GPT-5.6 Luna (high)openai0.283Ideal distance

Pareto-efficient: No
Question score: 17.74
Guesser cost / round: $0.0184

Claude Fable 5 (high)anthropic0.343Ideal distance

Pareto-efficient: Yes
Question score: 12.06
Guesser cost / round: $0.1776

GPT-5.6 Sol (high)openai0.350Ideal distance

Pareto-efficient: No
Question score: 14.40
Guesser cost / round: $0.1711

Kimi K3 (high)moonshotai0.396Ideal distance

Pareto-efficient: No
Question score: 12.74
Guesser cost / round: $0.2032

Gemini 3.6 Flash (high)google-vertex0.407Ideal distance

Pareto-efficient: No
Question score: 16.89
Guesser cost / round: $0.1705

GPT-6 Astra (high)openai0.665Ideal distance

Pareto-efficient: No
Question score: 15.09
Guesser cost / round: $0.3279

Mistral Medium 3.5 (high)mistral0.908Ideal distance

Pareto-efficient: No
Question score: 20.06
Guesser cost / round: $0.4113

Llama 4 Maverick (non-thinking)parasail1.000Ideal distance

Pareto-efficient: Yes
Question score: 32.23
Guesser cost / round: $0.0086

Claude Fable 5.1 (high)anthropic1.000Ideal distance

Pareto-efficient: No
Question score: 12.11
Guesser cost / round: $0.5014

1 model is not ranked because a question score or a Guesser cost above zero is missing.

How it is calculated

Distance from the lowest score and cost.

Both measures use a 0-to-1 scale and have equal weight. Lower is better.

Formula√(scaled question score² + scaled Guesser cost²)

Calculation detailsSteps and limits

Scale question score as (value − lowest) ÷ (highest − lowest) across the compared models.
Scale Guesser cost per round with the same calculation.
Measure straight-line distance from (0, 0). Lower is better.

A model with scaled question score 0.06 and scaled cost 0.08 has distance √(0.06² + 0.08²) = 0.10.

The question score includes the fixed score for failed rounds.

Adding or removing a model can change every scaled value and rank.