Value: quality per dollar

BenchLeader Index divided by the blended price per million tokens (3 input : 1 output). Higher means more quality for the money.

As of 24 Oct 2026, BenchLeader ranks Gemma 4 E4B first on the Value: quality per dollar board at 1112.5, ahead of Granite 4.2 3B (845.3) and Gemma 4 E2B (832.0).

287 models · data as of 24 Oct 2026

Model sizeAll 101Tiny 2Small 14Medium 7Large 36

• OpenAI13
• Alibaba11
• DeepSeek9
• Google9
• Mistral AI9
• Anthropic8
• Meta6
• Moonshot AI4
• NVIDIA4
• Xiaomi4
• Zhipu AI4
• IBM3
• SpaceXAI3
• Inception2
• MiniMax2
• Upstage2
• Ant Group1
• AApodex1

The dashed staircase is the efficiency frontier: at each price, the best index anyone reaches. A model above and left of the rest gives you more quality per dollar of real work. Size bands and run costs come from Artificial Analysis, which is the only source that publishes what a fixed batch of work actually cost.

1. 1Gemma 4 E4B (thinking)1112.5
2. 2Granite 4.2 3B845.3
3. 3Gemma 4 E2B (thinking)832.0
4. 4Qwen3.5-4B (thinking)776.7
5. 5LFM2 24B A2B769.8
6. 6Llama 3.1 8B752.1
7. 7Mistral Small 3677.6
8. 8Nova Micro609.2
9. 9NVIDIA Nemotron Nano 9B v2 (thinking)592.9
10. 10DeepSeek-R1-0528-Qwen3-8B552.9
11. 11Sarvam 105B (high)549.3
12. 12Gemma 3 4B547.6
13. 13Nemotron 3 Nano 30B A3B (thinking)528.4
14. 14Ling 3.0 Flash VL500.0
15. 15Nemotron 3.5 Lightning498.9

SearchAll providersAI21 LabsAlibabaAmazonAnt GroupAnthropicApodexArcee AIByteDanceCelerisCohereDeepSeekGoogleIBMInceptionLiquid AIMeituanMetaMicrosoftMiniMaxMistral AIMoonshot AIMultiverse ComputingNex AGINous ResearchNVIDIAOpenAIReflectionRekaSapiens AISarvamSpaceXAIStepFunSwiss AIThinking MachinesUpstageXiaomiZhipu AIOpen weightsNew models287 of 287

#	Model	Index per $ ↓	Index ↕	Blended $/M ↕
1	Gemma 4 E4BthinkingGoogleopen ↗	1112.5	44.5	$0.040
2	Granite 4.2 3BIBMopen ↗	845.3	44.8	$0.053
3	Gemma 4 E2BthinkingGoogleopen ↗	832.0	41.6	$0.050
4	Qwen3.5-4BthinkingAlibabaopen ↗	776.7	46.6	$0.060
5	LFM2 24B A2BLiquid AIopen ↗	769.8	40.8	$0.053
6	Llama 3.1 8BMetaopen ↗	752.1	36.1	$0.048
7	Mistral Small 3Mistral AIopen ↗	677.6	39.3	$0.058
8	Nova MicroAmazon	609.2	39.6	$0.065
9	NVIDIA Nemotron Nano 9B v2thinkingNVIDIAopen	592.9	41.5	$0.070
10	DeepSeek-R1-0528-Qwen3-8BDeepSeekopen ↗	552.9	37.6	$0.068
11	Sarvam 105BhighSarvamopen	549.3	40.1	$0.073
12	Gemma 3 4BGoogleopen ↗	547.6	34.5	$0.063
13	Nemotron 3 Nano 30B A3BthinkingNVIDIAopen ↗	528.4	46.5	$0.088
14	Ling 3.0 Flash VLAnt Groupopen ↗	500.0	55.5	$0.111
15	Nemotron 3.5 LightningNVIDIAopen ↗	498.9	47.4	$0.095
16	Gemma 3 12BGoogleopen ↗	492.0	36.9	$0.075
17	Ling 3.0 Flash FinAnt Groupopen	489.2	54.3	$0.111
18	Llama 3-8BMetaopen	480.8	35.1	$0.073
19	gpt-oss-20bhighOpenAIopen ↗	476.3	44.3	$0.093
20	Granite 3.3 8Bno reasoningIBMopen ↗	461.2	39.2	$0.085
21	Ling 3.0 FlashAnt Groupopen ↗	459.1	52.8	$0.115
22	Llama 3.2 1B InstructMetaopen ↗	456.3	32.4	$0.071
23	Granite 4.2 8BIBMopen ↗	426.9	46.1	$0.108
24	DeepSeek V4 Flash 0420maxDeepSeekopen	407.1	57.0	$0.140
25	GPT-5 nanoOpenAI	405.1	55.9	$0.138
26	Agnes 2.5 Pro BetaSapiens AI	394.0	59.1	$0.150
27	Mistral Small 3.1Mistral AIopen	382.1	36.3	$0.095
28	Mistral Small 3.2Mistral AIopen ↗	378.2	41.6	$0.110
29	Ministral 3 3BMistral AIopen ↗	370.0	37.0	$0.100
30	Nova LiteAmazon	364.8	38.3	$0.105
31	Step 3.5 FlashStepFunopen ↗	358.0	53.7	$0.150
32	MiMo-V2-FlashthinkingXiaomiopen ↗	349.3	52.4	$0.150
33	MiMo-V2.6-FlashXiaomiopen ↗	341.1	59.7	$0.175
34	DeepSeek V4 FlashmaxDeepSeekopen ↗	339.4	59.4	$0.175
35	Quasar 438BmaxMultiverse Computing	338.2	55.8	$0.165
36	Step 3.5 Flash 0202StepFunopen	338.0	50.7	$0.150
37	Llama 2-7BMetaopen ↗	338.0	33.8	$0.100
38	Gemma 4 12BthinkingGoogleopen ↗	336.7	50.5	$0.150
39	GLM 4.7 FlashZhipu AIopen ↗	335.3	51.3	$0.153
40	MiMo-V2.5Xiaomiopen ↗	329.1	54.3	$0.165
41	Qwen2.5 7B InstructAlibabaopen ↗	319.2	39.9	$0.125
42	Qwen3.5-9BthinkingAlibabaopen ↗	316.1	49.0	$0.155
43	Claude Haiku 5.5xhighAnthropic	307.5	61.5	$0.200
44	Qwen3 30B A3B 2507Alibabaopen ↗	304.0	45.6	$0.150
45	GPT-6 LunamaxOpenAI	300.0	60.0	$0.200
46	Apertus 8B InstructSwiss AIopen	299.2	37.4	$0.125
47	Qwen3.5 FlashAlibaba	297.1	52.0	$0.175
48	Llama 3.2 3B InstructMetaopen ↗	293.4	35.8	$0.122
49	Gemma 4 26B A4BGoogleopen ↗	283.8	56.2	$0.198
50	Devstral Small 2505Mistral AIopen	278.0	41.7	$0.150
51	Gemini 2.5 Flash-LiteGoogle	276.0	48.3	$0.175
52	Gemini 2.5 Flash Lite 09thinkingGoogle	273.7	47.9	$0.175
53	Phi-4-MiniMicrosoftopen ↗	265.2	35.8	$0.135
54	GLM 5.3 FlashZhipu AIopen ↗	263.0	62.6	$0.238
55	Qwen3.8-Flash-NextAlibabaopen ↗	261.7	60.2	$0.230
56	Gemma 3 27BGoogleopen ↗	259.3	38.9	$0.150
57	Ministral 3 8BMistral AIopen ↗	256.0	38.4	$0.150
58	Ministral 8BMistral AIopen	252.7	37.9	$0.150
59	NewMiniMax M3.1 FlashMiniMaxopen ↗	236.6	62.0	$0.262
60	Qwen3 30B A3BAlibabaopen ↗	224.7	48.3	$0.215

Show 100 more

Cite as: BenchLeader, “Value: quality per dollar”, data as of 24 Oct 2026, https://www.benchleader.com/leaderboards/value.