Benchmark-Snapshot: 2026-09-29

Name: LLM benchmark snapshot 2026-09-29
Creator: Wikiprompt
License: https://creativecommons.org/licenses/by-sa/4.0/

Von Wikiprompt, der freien Prompt-Enzyklopadie

Eingefrorenes Abbild der Rankings an diesem Datum. Die Live-Rangliste ist unter /benchmarks.

← 2026-09-27 2026-10-02 →

Text-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
3	claude-opus-5-max	anthropic	1,506	26,760
4	claude-opus-4-6-high	anthropic	1,504	76,518
5	claude-opus-5-high	anthropic	1,504	55,063
6	claude-opus-4-6	anthropic	1,498	80,836
7	gemini-3.8-flash-high	google	1,494	21,728
8	claude-fable-5-high	anthropic	1,491	36,462
10	claude-opus-4-7-high	anthropic	1,490	64,007
14	claude-opus-4-7	anthropic	1,484	65,051
15	gemini-3.5-flash-high	google	1,481	46,190
16	gemini-3.1-pro-preview	google	1,480	119,196
17	qwen3.8-max	alibaba	1,480	21,561
18	gemini-3-pro	google	1,479	41,921
19	muse-spark-1.1	meta	1,478	34,760
20	gemini-3.6-flash-high	google	1,478	33,739
22	gemini-3.5-flash-medium	google	1,476	44,906

Webentwicklungs-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	claude-opus-5.5-max	anthropic	1,827	1,607
2	gpt-6-astra-max	openai	1,792	4,908
3	claude-fable-5.1-max	anthropic	1,751	5,313
4	claude-opus-5-max	anthropic	1,693	15,627
5	gpt-6-sol-max	openai	1,681	2,019
6	qwen3.8-max	alibaba	1,672	3,469
7	claude-opus-5-high	anthropic	1,662	18,930
8	qwen3.8-max-0902	alibaba	1,662	6,203
9	kimi-k3-max	moonshot	1,660	14,739
10	muse-spark-1.3-max	meta	1,656	5,945
11	qwen3.8-flash-next	alibaba	1,636	4,980
12	hy4-preview	tencent	1,631	4,954
13	grok-4.7-xhigh	xai	1,629	2,047
14	claude-fable-5-high	anthropic	1,627	13,086
15	muse-spark-1.3 (xHigh)	meta	1,626	5,043

Vision-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	claude-fable-5-high	anthropic	1,326	13,483
2	claude-opus-5-high	anthropic	1,321	15,304
3	claude-fable-5.1-max	anthropic	1,319	4,050
4	claude-opus-4-7	anthropic	1,317	22,948
5	claude-opus-4-6-high	anthropic	1,316	22,350
6	qwen3.8-max	alibaba	1,314	10,086
7	gemini-3.7-flash-high	google	1,314	3,425
8	claude-opus-4-7-high	anthropic	1,314	22,559
9	claude-opus-4-6	anthropic	1,313	26,904
10	gemini-3.8-flash-high	google	1,312	2,711
11	gemini-3.5-flash-high	google	1,310	11,983
12	muse-spark-1.3-max	meta	1,310	3,472
13	gemini-3.5-flash-medium	google	1,308	12,124
14	muse-spark	meta	1,306	5,880
15	gemini-3-pro	google	1,305	13,624

Text-zu-Bild-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	gpt-image-2.5-sunburst	openai	1,424	10,884
2	gpt-image-2.5-flare	openai	1,401	10,058
3	gpt-image-2 (medium)	openai	1,383	88,744
4	mai-image-2.6	microsoft-ai	1,335	18,625
5	reve-2.1	reve	1,302	8,305
6	grok-imagine-image-2.0 (low)	xai	1,301	7,257
7	muse-image	meta	1,276	35,422
8	reve-2.0	reve	1,269	15,802
9	gemini-3.1-flash-image (nano-banana-2) [web-search]	google	1,261	53,228
10	seedream-5.0-pro	bytedance	1,256	85,690
11	qwen-image-3.0-pro	alibaba	1,256	11,520
12	mai-image-2.5	microsoft-ai	1,254	61,448
13	gemini-3.1-flash-lite-image (nano-banana-2-lite)	google	1,250	17,851
14	gemini-3-pro-image-2k (nano-banana-pro)	google	1,247	168,447
15	gpt-image-1.5-high-fidelity	openai	1,238	165,437

Bildbearbeitungs-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	gpt-image-2.5-sunburst	openai	1,526	29,252
2	gpt-image-2.5-flare	openai	1,482	27,048
3	gpt-image-2 (medium)	openai	1,461	259,008
4	grok-imagine-image-2.0 (low)	xai	1,430	16,842
5	mai-image-2.6	microsoft-ai	1,429	26,702
6	muse-image	meta	1,402	106,325
7	mai-image-2.5	microsoft-ai	1,400	174,678
8	seedream-5.0-pro	bytedance	1,394	226,513
9	gemini-3-pro-image-2k (nano-banana-pro)	google	1,390	582,162
10	grok-imagine-image-quality (20260519)	xai	1,390	35,596
11	chatgpt-image-latest-high-fidelity (20251216)	openai	1,388	565,718
12	gemini-3.1-flash-image (nano-banana-2) [web-search]	google	1,388	183,488
13	gemini-3-pro-image-preview (nano-banana-pro)	google	1,385	518,488
14	reve-2.1	reve	1,375	19,123
15	gpt-image-1.5-high-fidelity	openai	1,370	589,013

Text-zu-Video-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	gemini-omni-1.1-flash	google	1,516	1,784
2	gemini-omni-flash	google	1,513	26,576
3	flux-3-video	bfl	1,493	1,302
4	grok-imagine-video-1.5-agent	xai	1,492	1,218
5	dreamina-seedance-2.0-720p	bytedance	1,479	56,318
6	wan3.0	alibaba	1,476	2,598
7	dreamina-seedance-2.5-720p	bytedance	1,474	8,001
8	minimax-h3	minimax	1,460	11,417
9	muse-video	meta	1,456	2,188
10	happyhorse-1.0	aorizon	1,427	22,264
11	sora-2-pro	openai	1,368	54,167
12	veo-3.1-audio	google	1,364	13,741
13	veo-3.1-audio-1080p	google	1,362	25,076
14	veo-3.1-fast-audio	google	1,362	39,484
15	veo-3.1-fast-audio-1080p	google	1,358	25,870

Videobearbeitungs-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	wan3.0	alibaba	1,414	463
2	dreamina-seedance-2.5-720p	bytedance	1,410	429
3	minimax-h3	minimax	1,392	962
4	gemini-omni-flash	google	1,367	2,109
5	dreamina-seedance-2.0-720p	bytedance	1,365	3,852
6	happyhorse-1.0	aorizon	1,307	3,116
7	grok-imagine-video	xai	1,258	13,724
8	kling-o3-pro	kling	1,255	7,540
9	kling-o1-pro	kling	1,197	10,542
10	runway-gen4-aleph	runway	1,182	9,818

Such-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	gpt-5.6-sol-xhigh	openai	1,257	29,663
2	claude-opus-4-6-search	anthropic	1,253	134,699
3	gpt-5.5-search	openai	1,242	89,873
4	claude-opus-4-7	anthropic	1,233	91,394
5	claude-fable-5	anthropic	1,230	41,795
6	ernie-5.1	baidu	1,227	3,788
7	claude-sonnet-4-6-search	anthropic	1,221	134,905
8	grok-4.5	xai	1,213	31,505
9	gemini-3.1-pro-grounding	google	1,210	113,282
10	gemini-3-pro-grounding	google	1,207	37,024
11	gpt-5.2-search	openai	1,207	52,712
12	claude-opus-4-8	anthropic	1,204	70,998
13	grok-4.20-multi-agent-beta-0309	xai	1,204	109,553
14	gpt-5.1-search	openai	1,199	59,909
15	gemini-3-flash-grounding	google	1,198	149,334

Agenten-Arena

Rang	Modell	Organisation
1	Claude Fable 5.1 (Max)	anthropic
2	Claude Opus 5.5 (High)	anthropic
3	GPT 6 Astra (Max)	openai
4	Claude Opus 5 (Max)	anthropic
5	Claude Opus 5 (High)	anthropic
6	GPT 6 Sol (Max)	openai
7	Claude Fable 5 (High)	anthropic
8	Claude Opus 4.8 (High)	anthropic
9	GPT 5.6 Sol (xHigh)	openai
10	Claude Sonnet 5 (High)	anthropic
11	GPT 5.5 (xHigh)	openai
12	Hy4 preview	tencent
13	Kimi K3 (Max)	moonshot
14	Grok 4.7 (xHigh)	xai
15	Deepseek V4.1 Flash (Max)	deepseek

Dokumenten-Arena

Rang	Modell	Organisation	Elo-Wert	Stimmen
1	claude-opus-5-high	anthropic	1,516	8,794
2	claude-fable-5.1-max	anthropic	1,513	1,403
3	claude-opus-4-6-high	anthropic	1,507	27,929
4	claude-opus-4-6	anthropic	1,507	41,260
5	claude-fable-5	anthropic	1,496	8,497
6	claude-opus-4-7	anthropic	1,495	22,192
7	claude-opus-4-7-high	anthropic	1,495	21,957
8	gpt-5.5	openai	1,486	21,279
9	gpt-5.5-high	openai	1,484	20,944
10	gpt-5.6-sol-xhigh	openai	1,483	4,818
11	claude-sonnet-4-6	anthropic	1,482	57,813
12	claude-opus-4-8-high	anthropic	1,475	11,551
13	gpt-5.6-terra-xhigh	openai	1,472	5,787
14	gpt-5.4	openai	1,471	33,331
15	muse-spark-1.3-max	meta	1,471	1,006

Weitere Ranglisten

LiveBench

Metrik: average score (0-100) · livebench.ai

Rang	Modell	Wert
1	claude-fable-5-1-max-effort	83.8
2	claude-fable-5-max-effort	83.4
3	claude-opus-5-5-max-effort	83.2
4	gpt-6-astra-max	83.1
5	muse-spark-1.3-xhigh	82.4
6	claude-opus-5-5-xhigh-effort	82.1
7	gpt-5.6-sol-max	81.7
8	deepseek-v4.1-flash-max	81.5
9	gpt-5.5-xhigh	80.8
10	claude-opus-5-max-effort	80.5
11	gemini-3.7-flash-high	79.9
12	gpt-6-sol-max	79.8
13	smaug-agentic	79.7
14	qwen3.8-max	79.5
15	kimi-k3	79.5

Aider polyglot (coding)

Metrik: pass rate 2 (%) · aider.chat/docs/leaderboards/

Rang	Modell	Wert
1	gpt-5 (high)	88
2	gpt-5 (medium)	86.7
3	o3-pro (high)	84.9
4	gemini-2.5-pro-preview-06-05 (32k think)	83.1
5	o3 (high)	81.3
6	gpt-5 (low)	81.3
7	grok-4 (high)	79.6
8	gemini-2.5-pro-preview-06-05 (default think)	79.1
9	o3 (high) + gpt-4.1	78.2
10	Gemini 2.5 Pro Preview 05-06	76.9
11	o3	76.9
12	DeepSeek-V3.2-Exp (Reasoner)	74.2
13	Gemini 2.5 Pro Preview 03-25	72.9
14	o4-mini (high)	72
15	claude-opus-4-20250514 (32k thinking)	72

Artificial Analysis (Intelligence Index)

Metrik: AA Intelligence Index (0-100) · artificialanalysis.ai

Rang	Modell	Organisation	Wert
1	Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	57.6
2	Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	56
3	Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	56
4	Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	53.6
5	Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	53.4
6	Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	53.2
7	GPT-6 Astra (max)	OpenAI	52.7
8	GPT-6 Astra (xhigh)	OpenAI	52.4
9	Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	51.9
10	Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	51.2
11	Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	51.2
12	GPT-6 Astra (high)	OpenAI	50.9
13	Claude Opus 5 (Adaptive Reasoning, Max Effort)	Anthropic	50.8
14	Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	49.7
15	Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	49.6

BenchLM

Metrik: aggregated display score · benchlm.ai

Rang	Modell	Organisation	Wert
1	GPT-6 Astra	OpenAI	88.5
2	Claude Opus 5.5	Anthropic	87.1
3	Claude Fable 5.1	Anthropic	83
4	GPT-6 Sol	OpenAI	81.1
5	Claude Sonnet 5.5	Anthropic	80.5
6	Claude Opus 5	Anthropic	79.6
7	Claude Fable 5	Anthropic	78.9
8	GPT-5.6 Sol	OpenAI	78.4
9	MiMo-V2.6-Pro	Xiaomi	74.7
10	Gemini 3.8 Flash	Google	73.5
11	GPT-5.6 Terra	OpenAI	72.6
12	GPT-5.5 Pro	OpenAI	72.4
13	Kimi K3	Moonshot AI	71.9
14	Qwen3.8 Max	Alibaba	71.7
15	GPT-5.4 Pro	OpenAI	70.8

Quellen und Methodik

Die Ranglisten werden aus offenen Community-Bewertungen aggregiert. Elo-Werte, Konfidenzintervalle und Stimmen stammen von LMArena (Community-Votings in direkten Modell-Duellen, als offenes Dataset veroffentlicht). Preise und Kontext-Metadaten stammen aus der offentlichen OpenRouter-API. Wikiprompt erstellt taglich einen Snapshot und bewahrt die Historie; eigene Evaluationen fuhren wir nicht durch.