Modelrankings

Open modellen gerangschikt op intelligentie en snelheid, gehost op GPU's in de EU.

Probeer ze gratis Volledige catalogus →

Bench: gemeten kwaliteit van onze modellen

De 50 beste modellen die wij hosten, alleen gemeten cijfers (Epoch AI, of LiveBench en LMArena omgerekend naar dezelfde schaal); schattingen staan niet in de ranglijst.

#	Model	Bron	Bandbreedte	LiveBench	Bench
1	Kimi K3 Moonshotai	Gemeten	81.4-88.3	79.2	84.6
2	GLM 5.3 Z.AI	Gemeten	79.5-85.0	76.1	82.0
3	DeepSeek V4 Pro 0813 DeepSeek	Gemeten	79.6-84.1	77.4	81.7
4	DeepSeek V4.1 Flash DeepSeek	Gemeten	73.2-84.4	81.1	81.3
5	DeepSeek V4 Flash Vision Exp DeepSeek	Via LiveBench	71.3-83.9	76.8	77.6
6	GLM 5.3 Flash Z.AI	Gemeten	74.5-80.3	71.6	77.4
7	GLM 5.2 Z.AI	Gemeten	74.9-79.5	73.2	77.2
8	Qwen3.8 Flash Next Qwen	Via LiveBench	70.9-83.5	76.2	77.2
9	Kimi K2.6 Moonshotai	Gemeten	73.9-78.5	70.5	76.3
10	Kimi K2.7 Code Moonshotai	Gemeten	72.7-77.1	68.4	75.0
11	GLM 5.1 Z.AI	Gemeten	72.4-77.0	70.2	74.8
12	Qwen3.8 27B Qwen	Gemeten	71.8-76.6	75.3	74.2
13	DeepSeek V4 Pro DeepSeek	Gemeten	71.8-76.0	71.6	73.9
14	Kimi K2.5 Moonshotai	Gemeten	70.3-74.1	69.1	72.6
15	gemma 4 31B Google	Via LMArena	63.8-79.7	—	71.8
16	MiniMax M3 MiniMaxAI	Gemeten	66.2-74.6	67.3	71.3
17	MiniMax M2.5 MiniMaxAI	Gemeten	65.9-72.3	60.2	70.9
18	Qwen3.5 397B A17B Qwen3.5-397b-a17b	Gemeten	68.5-72.8	—	70.8
19	Qwen3.6 27B Qwen	Gemeten	67.6-72.2	64.0	70.6
20	DeepSeek V3.2 DeepSeek	Gemeten	67.5-71.8	51.8	70.4
21	DeepSeek V4 Flash DeepSeek	Gemeten	66.8-72.2	74.2	70.1
22	Kimi K2 Thinking Moonshotai	Gemeten	66.2-71.8	61.6	70.0
23	NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 NVIDIA	Via LiveBench	63.6-76.2	67.4	69.9
24	GLM 5 Z.AI	Gemeten	67.2-72.1	68.9	69.8
25	DeepSeek V3.2 Exp DeepSeek	Gemeten	65.4-71.2	49.9	68.8
26	Qwen3 VL 235B A22B Instruct Qwen	Via LMArena	60.3-76.2	—	68.3
27	GLM 4.5 Z.AI	Via LiveBench	61.6-74.3	65.0	68.0
28	Qwen3.5 122B A10B Qwen	Via LMArena	59.9-75.8	—	67.8
29	Qwen3.5 122B A10B Qwen	Via LMArena	59.9-75.8	—	67.8
30	DeepSeek V3.1 Terminus DeepSeek	Via LiveBench	61.4-74.0	64.7	67.7
31	Qwen3.6 35B A3B Qwen	Gemeten	64.0-70.1	—	67.4
32	GLM 4.7 Z.AI	Gemeten	63.8-69.4	58.1	66.9
33	Loes Large Qwen	Via LMArena	58.6-74.5	—	66.6
34	Qwen3.5 27B Qwen	Via LMArena	58.6-74.5	—	66.6
35	Qwen3.5 27B Qwen	Via LMArena	58.6-74.5	—	66.6
36	gemma 4 31B Google	Gemeten	62.2-68.6	61.6	65.9
37	Qwen3.5 35B A3B Qwen	Gemeten	62.6-68.4	—	65.7
38	gemma 4 26B A4B Google	Gemeten	60.3-66.9	—	64.8
39	GLM 4.5 Air Z.AI	Via LiveBench	58.0-70.6	60.5	64.3
40	DeepSeek R1 0528 DeepSeek	Gemeten	61.0-66.4	69.4	64.1
41	Kimi K2 Instruct Moonshotai	Gemeten	57.6-65.3	48.1	62.7
42	GPT-OSS 120B Gpt-oss-120b	Gemeten	56.7-65.6	46.1	62.4
43	DeepSeek V3.1 DeepSeek	Gemeten	56.6-66.5	—	62.4
44	Qwen3.5 9B Qwen	Gemeten	57.8-64.1	—	61.8
45	Qwen3 235B A22B Qwen	Gemeten	56.6-63.5	63.4	61.7
46	DeepSeek R1 DeepSeek	Gemeten	57.5-63.0	72.7	61.2
47	Qwen3 235B A22B Instruct Qwen3-235b-a22b-instruct-2507	Gemeten	56.8-63.5	48.8	61.2
48	Phi 4 reasoning plus Microsoft	Via LiveBench	54.8-67.4	56.6	61.1
49	Qwen3 32B Qwen	Gemeten	55.9-63.1	43.6	60.6
50	Qwen3 14B Qwen	Gemeten	54.2-62.6	68.2	60.3

Bronnen: Epoch AI en LMArena (CC BY 4.0), LiveBench. Elke ochtend bijgewerkt. epoch.ai ↗

Intelligentie-ranglijst

Gerangschikt op een samengestelde index van openbaar gerapporteerde benchmarks. Hoger is beter.

#	Model	Grootte	MMLU	GPQA	MATH	Code	Index
1	DeepSeek R1 0528 DeepSeek	—	91.4	81.0	97.0	92.0	90.4
2	GPT-OSS 120B Gpt-oss-120b	—	—	80.1	97.9	—	89.0
3	DeepSeek R1 DeepSeek	—	90.8	71.5	97.3	90.0	87.4
4	GLM 4.6 Z.AI	—	85.5	82.0	93.5	—	87.0
5	GLM 4.5 Z.AI	—	84.6	79.1	91.0	—	84.9
6	Qwen2.5 32B Qwen	32B	83.3	—	83.1	88.4	84.9
7	gpt oss 20b OpenAI	21B	—	71.5	96.0	—	83.8
8	Qwen3 235B A22B Qwen	235B	87.8	71.1	92.2	—	83.7
9	DeepSeek V3.1 DeepSeek	—	90.0	67.0	92.0	85.0	83.5
10	DeepSeek V3 (685B MoE) DeepSeek	685B	89.5	62.7	91.6	84.0	82.0
11	GLM 4.5 Air Z.AI	110B	81.0	75.0	89.0	—	81.7
12	Qwen 2.5 14B Qwen	14B	79.7	—	80.0	83.5	81.1
13	DeepSeek V3 DeepSeek	—	88.5	59.1	90.2	82.6	80.1
14	DeepSeek R1 Distill Llama 70B DeepSeek	70B	—	65.2	94.5	—	79.9
15	Qwen3 32B Qwen	32B	82.4	68.4	88.5	—	79.8
16	DeepSeek R1 Distill 32B DeepSeek	32B	—	62.1	94.3	—	78.2
17	Qwen3 14B Qwen	14B	80.7	65.8	87.7	—	78.1
18	Qwen3 30B A3B Qwen	30B	79.5	65.8	86.6	—	77.3
19	DeepSeek R1 Distill 14B DeepSeek	14B	—	59.1	93.9	—	76.5
20	Qwen 2.5 72B Qwen	72B	86.1	49.0	83.1	86.6	76.2
21	Phi 4 (14B) Microsoft	14B	84.8	56.1	80.4	82.6	76.0
22	Llama 3.3 70B Meta	70B	86.0	50.5	77.0	88.4	75.5
23	Llama 3.1 405B Instruct Meta	405B	87.3	50.7	73.8	89.0	75.2
24	Qwen 2.5 Coder 32B Qwen	32B	—	—	57.2	92.7	75.0
25	Qwen3 8B Qwen	8B	76.9	62.0	85.0	—	74.6
26	Qwen 2.5 Coder 7B Qwen	7B	—	—	57.2	88.4	72.8
27	DeepSeek R1 Distill Qwen 7B DeepSeek	7.6B	—	49.1	92.8	—	71.0
28	Llama 3.1 70B Meta	70B	83.6	41.7	68.0	80.5	68.5
29	Qwen2.5 7B Qwen	7B	74.2	36.4	75.5	84.8	67.7
30	Phi 4 Mini (3.8B) Microsoft	3.8B	67.3	—	64.0	—	65.7
31	Gemma 3 27B Google	27B	—	42.4	89.0	—	65.7
32	gemma 3 12b Google	12B	—	34.9	83.8	—	59.4
33	gemma 2 27b it Google	27B	75.2	—	42.3	—	58.8
34	Phi 3.5 mini instruct Microsoft	3.8B	69.0	—	48.5	—	58.8
35	Llama 3.1 8B Meta	8B	69.4	30.4	51.9	72.6	56.1
36	Llama 3.2 3B Meta	3B	63.4	—	48.0	—	55.7
37	gemma 2 9b it Google	9.2B	71.3	—	36.6	—	54.0
38	Gemma 3 4B Google	4B	—	30.8	75.6	—	53.2
39	Mistral Nemo 12BEU Mistral	12B	68.0	—	38.0	—	53.0
40	Llama 3.2 1B Meta	1B	49.3	—	30.6	—	40.0
41	Mistral 7B Instruct v0.2EU Mistral	7.2B	60.1	—	11.2	30.5	33.9

Benchmarks zijn openbaar gerapporteerde cijfers van de modelmakers en open leaderboards (laatst bijgewerkt 2026-06). De methodiek verschilt per model, dus de index is een ordening, geen gecontroleerde benchmark.

Snelheidsranglijst

Gerangschikt op de werkelijke responstijd die wij op onze eigen EU-GPU's hebben gemeten. Lager is beter.

#	Model	Grootte	Responstijd
1	codegemma 2b Google	2.5B	66 ms
2	gemma 2b it Google	2.5B	67 ms
3	Llama 3.2 3B Instruct Meta	3.2B	76 ms
4	Apertus v1.1 1.5B InstructEU Swiss-ai	1.5B	81 ms
5	Flor 6.3B Instruct 4096EU BSC-LT	6.2B	81 ms
6	Phi 3 mini 128k instruct Microsoft	3.8B	81 ms
7	Phi 3.5 mini instruct Microsoft	3.8B	82 ms
8	granite vision 3.1 2b preview Ibm-granite	3B	83 ms
9	Llama 3.2 1B Instruct Meta	1.2B	87 ms
10	Meta Llama 3 8B Instruct Meta	8B	89 ms
11	Phi 3.5 vision instruct Microsoft	4.1B	93 ms
12	Qwen3 VL 2B Instruct Qwen	2.1B	93 ms
13	Flor 6.3B InstructEU BSC-LT	6.2B	94 ms
14	Qwen3.5 2B Qwen	2B	96 ms
15	Qwen3.5 0.8B Qwen	0.9B	96 ms
16	Qwen2.5 14B Instruct Qwen	15B	98 ms
17	phi 4 Microsoft	15B	98 ms
18	Qwen2.5 VL 7B Surg CholecT50 NVIDIA	8.3B	101 ms
19	salamandra 7b instruct tools 16kEU BSC-LT	7.8B	102 ms
20	salamandra 7b instruct 2606EU BSC-LT	7.8B	103 ms
21	Phi 4 mini instruct Microsoft	3.8B	103 ms
22	X Reasoner 7B Microsoft	8.3B	106 ms
23	EuroLLM 22B Instruct PreviewEU Utter-project	23B	109 ms
24	Llama Poro 2 8B SFTEU LumiOpen	8B	109 ms
25	EuroVLM 1.7B PreviewEU Utter-project	2.1B	110 ms

Responstijden zijn gemeten bij onze laatste verificatie per model en variëren met belasting en koude start.

Host. Route. Ship.

Geen creditcard nodig. Betaal naar gebruik, stop wanneer je wilt.

Begin vandaag gratis met hosten