RunwayVideo model
Runway Gen-4.5
In text to video, Runway Gen-4.5 is in place 17 of 23. A 5 s clip costs about $0.60.
1,225Arena ratinghigher is better
$0.60$0.12 per secondlower is better
10slongest single cliphigher is better
53out of 100same as last month
Summary
At $0.12 per second of video it is fairly cheap; a typical video model costs $0.12.
What is distinctive about Runway Gen-4.5 is its controlled short-clip direction from text or an image. A single prompt can describe camera choreography, scene composition, timing, and atmospheric changes in sequence. Output ranges from 2 to 10 seconds at 720p and 24 or 25 frames per second.
Runway provides Gen-4.5 through its web app and an eligible plan.
Runway Gen-4.5 benchmarks
Text to video arena
How people rate generated videos in blind comparisons, Elo points · higher is better
20 of 23 models
as of September 22, 2026 · Source: LMArena
Show all 74 individual results from 11 sources
Page 1 of 7
Published benchmarks
LMArena Text to Video
Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.
higher is betterAs of November 5, 2026Scale: 0 Elo - 1,516 Elo
Methodology and context
- Metric
- elo-rating
- Scale
- No upper bound is documented. The chart spans the recorded values and zero.
- Participants
- 23
- Sample
- 48,127
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
VGI-Bench visual-intelligence score (Show measurement, test conditions, and source)
- Source value
- 36.6
- Score
- 36.6
- Metric
- Overall final score
- Unit
- No unit provided
- Benchmark version
- arXiv:2608.19583v3 (Table 2)
- Category
- image-to-video-reasoning
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- VGI-Bench, arXiv:2608.19583v3
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Image-to-video visual-reasoning tasks; text prompt plus input image; 1280×720, 5 or 10 seconds at 24 fps. The common paper protocol evaluates half of each task's instances using a fixed random seed.
- Context
- The tables do not specify a score unit or per-model sample count. No percentage interpretation or denominator is inferred.
VGI-Bench visual-intelligence score (Show measurement, test conditions, and source)
- Source value
- 46.9
- Score
- 46.9
- Metric
- Visual Organization domain average
- Unit
- No unit provided
- Benchmark version
- arXiv:2608.19583v3 (Table 2)
- Category
- visual-organization
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- VGI-Bench, arXiv:2608.19583v3
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Image-to-video visual-reasoning tasks; text prompt plus input image; 1280×720, 5 or 10 seconds at 24 fps. The common paper protocol evaluates half of each task's instances using a fixed random seed.
- Context
- The tables do not specify a score unit or per-model sample count. No percentage interpretation or denominator is inferred.
VGI-Bench visual-intelligence score (Show measurement, test conditions, and source)
- Source value
- 34.8
- Score
- 34.8
- Metric
- Spatiotemporal Dynamics domain average
- Unit
- No unit provided
- Benchmark version
- arXiv:2608.19583v3 (Table 2)
- Category
- spatiotemporal-dynamics
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- VGI-Bench, arXiv:2608.19583v3
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Image-to-video visual-reasoning tasks; text prompt plus input image; 1280×720, 5 or 10 seconds at 24 fps. The common paper protocol evaluates half of each task's instances using a fixed random seed.
- Context
- The tables do not specify a score unit or per-model sample count. No percentage interpretation or denominator is inferred.
VGI-Bench visual-intelligence score (Show measurement, test conditions, and source)
- Source value
- 22.9
- Score
- 22.9
- Metric
- Structured Puzzles domain average
- Unit
- No unit provided
- Benchmark version
- arXiv:2608.19583v3 (Table 2)
- Category
- structured-puzzles
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- VGI-Bench, arXiv:2608.19583v3
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Image-to-video visual-reasoning tasks; text prompt plus input image; 1280×720, 5 or 10 seconds at 24 fps. The common paper protocol evaluates half of each task's instances using a fixed random seed.
- Context
- The tables do not specify a score unit or per-model sample count. No percentage interpretation or denominator is inferred.
VGI-Bench visual-intelligence score (Show measurement, test conditions, and source)
- Source value
- 45
- Score
- 45
- Metric
- Physical Manipulation domain average
- Unit
- No unit provided
- Benchmark version
- arXiv:2608.19583v3 (Table 2)
- Category
- physical-manipulation
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- VGI-Bench, arXiv:2608.19583v3
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Image-to-video visual-reasoning tasks; text prompt plus input image; 1280×720, 5 or 10 seconds at 24 fps. The common paper protocol evaluates half of each task's instances using a fixed random seed.
- Context
- The tables do not specify a score unit or per-model sample count. No percentage interpretation or denominator is inferred.
Video Models AI-judge benchmark (Show measurement, test conditions, and source)
- Source value
- 3.67
- Score
- 3.67
- Metric
- Weighted overall AI-judge quality score (0-5)
- Unit
- points
- Benchmark version
- Video Models leaderboard updated 2026-10-15
- Category
- video-generation
- Direction
- Higher is better
- Sample
- 64
- Source type
- vendor-reported
- Evaluator
- Video Models by Wiro AI
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact Wiro API route runway/gen-4-5. Published method states one API run per prompt using model defaults, first successful output, a 5-second duration target, and the resolution closest to 720p. This route documentation lists 2-10s; output capped at 720p. The CSV does not expose the exact per-prompt overrides or criterion-specific denominators.
- Context
- Wiro AI is a commercial model gateway. Scores use its weighted 0-5 AI-judge rubric, not a blind human pairwise preference panel. No per-criterion N or confidence interval is published. This is task-specific AI-judge evidence, not broad independent quality proof.
Video Models AI-judge benchmark (Show measurement, test conditions, and source)
- Source value
- 3.34
- Score
- 3.34
- Metric
- Prompt adherence AI-judge criterion score (0-5); rubric weight 21%
- Unit
- points
- Benchmark version
- Video Models leaderboard updated 2026-10-15
- Category
- video-generation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Video Models by Wiro AI
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact Wiro API route runway/gen-4-5. Published method states one API run per prompt using model defaults, first successful output, a 5-second duration target, and the resolution closest to 720p. This route documentation lists 2-10s; output capped at 720p. The CSV does not expose the exact per-prompt overrides or criterion-specific denominators.
- Context
- Wiro AI is a commercial model gateway. Scores use its weighted 0-5 AI-judge rubric, not a blind human pairwise preference panel. No per-criterion N or confidence interval is published. This is task-specific AI-judge evidence, not broad independent quality proof.
Video Models AI-judge benchmark (Show measurement, test conditions, and source)
- Source value
- 3.52
- Score
- 3.52
- Metric
- Motion and consistency AI-judge criterion score (0-5); rubric weight 19%
- Unit
- points
- Benchmark version
- Video Models leaderboard updated 2026-10-15
- Category
- video-generation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Video Models by Wiro AI
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact Wiro API route runway/gen-4-5. Published method states one API run per prompt using model defaults, first successful output, a 5-second duration target, and the resolution closest to 720p. This route documentation lists 2-10s; output capped at 720p. The CSV does not expose the exact per-prompt overrides or criterion-specific denominators.
- Context
- Wiro AI is a commercial model gateway. Scores use its weighted 0-5 AI-judge rubric, not a blind human pairwise preference panel. No per-criterion N or confidence interval is published. This is task-specific AI-judge evidence, not broad independent quality proof.
Video Models AI-judge benchmark (Show measurement, test conditions, and source)
- Source value
- 3.87
- Score
- 3.87
- Metric
- Camera and framing AI-judge criterion score (0-5); rubric weight 12%
- Unit
- points
- Benchmark version
- Video Models leaderboard updated 2026-10-15
- Category
- video-generation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Video Models by Wiro AI
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact Wiro API route runway/gen-4-5. Published method states one API run per prompt using model defaults, first successful output, a 5-second duration target, and the resolution closest to 720p. This route documentation lists 2-10s; output capped at 720p. The CSV does not expose the exact per-prompt overrides or criterion-specific denominators.
- Context
- Wiro AI is a commercial model gateway. Scores use its weighted 0-5 AI-judge rubric, not a blind human pairwise preference panel. No per-criterion N or confidence interval is published. This is task-specific AI-judge evidence, not broad independent quality proof.
Video Models AI-judge benchmark (Show measurement, test conditions, and source)
- Source value
- 4.13
- Score
- 4.13
- Metric
- Quality and detail AI-judge criterion score (0-5); rubric weight 11%
- Unit
- points
- Benchmark version
- Video Models leaderboard updated 2026-10-15
- Category
- video-generation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Video Models by Wiro AI
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact Wiro API route runway/gen-4-5. Published method states one API run per prompt using model defaults, first successful output, a 5-second duration target, and the resolution closest to 720p. This route documentation lists 2-10s; output capped at 720p. The CSV does not expose the exact per-prompt overrides or criterion-specific denominators.
- Context
- Wiro AI is a commercial model gateway. Scores use its weighted 0-5 AI-judge rubric, not a blind human pairwise preference panel. No per-criterion N or confidence interval is published. This is task-specific AI-judge evidence, not broad independent quality proof.
Video Models AI-judge benchmark (Show measurement, test conditions, and source)
- Source value
- 4.22
- Score
- 4.22
- Metric
- Look and lighting AI-judge criterion score (0-5); rubric weight 9%
- Unit
- points
- Benchmark version
- Video Models leaderboard updated 2026-10-15
- Category
- video-generation
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Video Models by Wiro AI
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Vendor-reported result. Exact Wiro API route runway/gen-4-5. Published method states one API run per prompt using model defaults, first successful output, a 5-second duration target, and the resolution closest to 720p. This route documentation lists 2-10s; output capped at 720p. The CSV does not expose the exact per-prompt overrides or criterion-specific denominators.
- Context
- Wiro AI is a commercial model gateway. Scores use its weighted 0-5 AI-judge rubric, not a blind human pairwise preference panel. No per-criterion N or confidence interval is published. This is task-specific AI-judge evidence, not broad independent quality proof.
Recorded measurement details
LMArena Text to Video: LMArena Text to Video (Show measurement, test conditions, and source)
- Source value
- 1225
- Score
- 1225
- Metric
- elo-rating
- Unit
- Elo
- Task
- lmarena-text-to-video
- Task label
- LMArena Text to Video
- Direction
- Higher is better
- Source rank
- 27
- Sample
- 48127
- Lower confidence bound
- 1217
- Upper confidence bound
- 1233
- Retrieved at
- 2026-11-05
Page 1 of 7
Video sample from our test
This video exists as a documented run for the exact model version. Playback is muted.
Motion and physical consistency
This sample tests Anatomy, object consistency, camera tracking, rain, and reflections.
Prompt and settings
Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.
Generated through OpenRouter with model runway/gen-4.5. Archived settings were 16:9, one request, first output, requested 5 s, request {"model":"runway/gen-4.5","prompt":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","aspect_ratio":"16:9","duration":5,"resolution":"720p","generate_audio":false}, live estimated cost $0.6000, actual cost $0.6000.
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
0 to 100, higher is more popular
20 of 98 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 5, 2026
Runway Gen-4.5Veo 3.1Sora 2Muse VideoFLUX.3 Video
Runway Gen-4.5 compared
Compare with another model
The most popular comparisons
- 1Veo 3.1 vs. Runway Gen-4.5
- 2Gemini Omni Flash vs. Runway Gen-4.5
- 3FLUX.3 Video vs. Runway Gen-4.5
- 4Dreamina Seedance 2.5 720p vs. Runway Gen-4.5
- 5Dreamina Seedance 2.0 720p vs. Runway Gen-4.5
- 6MiniMax H3 vs. Runway Gen-4.5
- 7Sora 2 Pro vs. Runway Gen-4.5
- 8Sora 2 vs. Runway Gen-4.5
- 9Veo 3.1 Fast vs. Runway Gen-4.5
Show all 48 comparisons
- 10Grok Imagine Video 1.5 vs. Runway Gen-4.5
- 11Grok Imagine Video vs. Runway Gen-4.5
- 12Wan 2.7 vs. Runway Gen-4.5
- 13Wan 2.6 vs. Runway Gen-4.5
- 14Runway Gen-4.5 vs. Kling 3.0 Pro
- 15Runway Gen-4.5 vs. Kling 2.6 Pro
- 16Runway Gen-4.5 vs. Vidu Q3 Pro
- 17Runway Gen-4.5 vs. PixVerse V5.6
- 18Runway Gen-4.5 vs. Hailuo 2.3
- 19Runway Gen-4.5 vs. LTX-2 19B
- 20Runway Gen-4.5 vs. Wan 2.2 A14B
- 21Runway Gen-4.5 vs. HunyuanVideo 1.5
- 22Runway Gen-4.5 vs. Pika 2.2
- 23Runway Gen-4.5 vs. Gemini Omni 1.1 Flash
- 24Runway Gen-4.5 vs. Muse Video
- 25Runway Gen-4.5 vs. Wan 3.0
- 26Runway Gen-4.5 vs. Wan 3.0 Prime
- 27Runway Gen-4.5 vs. HappyHorse 1.0
- 28Runway Gen-4.5 vs. HappyHorse 1.1
- 29Runway Gen-4.5 vs. PixVerse V6
- 30Runway Gen-4.5 vs. PixVerse C1
- 31Runway Gen-4.5 vs. Seedance 2.0 Fast
- 32Runway Gen-4.5 vs. Seedance 2.0 Mini
- 33Runway Gen-4.5 vs. Vidu Q3 Turbo
- 34Runway Gen-4.5 vs. Vidu Q2
- 35Runway Gen-4.5 vs. Vidu Q1
- 36Runway Gen-4.5 vs. Kling 4.0
- 37Runway Gen-4.5 vs. Kling 3.0 Standard API
- 38Runway Gen-4.5 vs. Kling Video O1
- 39Runway Gen-4.5 vs. Hailuo 2.3 Fast
- 40Runway Gen-4.5 vs. Wan 2.5 Preview
- 41Runway Gen-4.5 vs. Wan 2.6 I2V Flash
- 42Runway Gen-4.5 vs. Wan 2.2 TI2V 5B
- 43Runway Gen-4.5 vs. Wan 2.2 I2V A14B
- 44Runway Gen-4.5 vs. HunyuanVideo 1.0 T2V
- 45Runway Gen-4.5 vs. HunyuanVideo I2V 1.0
- 46Runway Gen-4.5 vs. Ray 3.2
- 47Runway Gen-4.5 vs. Grok Imagine Video 1.5 Lite
- 48Runway Gen-4.5 vs. LTX-2.5
All specifications
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Prices
At Runway from ≈ €15.90 a month (Runway Standard, with limited credits). Through other providers from ≈ €6.36 a month (ElevenLabs Starter, with limited credits). 34 plans in Germany.
| Plan | Monthly price | Note |
|---|---|---|
| Runway Standard | ≈ €15.90 | developer's own plan, with limited credit |
| Runway Pro | ≈ €37.11 | developer's own plan, with limited credit |
| Runway Team | ≈ €73.16 | developer's own plan, with limited credit, for teams, per seat |
| Runway Max | ≈ €100.72 | developer's own plan, with limited credit |
| Runway Enterprise | n/a | developer's own plan, for enterprises |
| ElevenLabs Starter | ≈ €6.36 | with limited credit |
| Poe Basic | €6.83 | with limited credit |
| Krea Basic | ≈ €9.54 | with limited credit |
| Adobe Firefly Standard | €10.98 | with limited credit |
| Magnific Premium | €19.04 | with limited credit |
| Adobe Firefly Pro | €21.99 | with limited credit |
| ElevenLabs Creator | ≈ €23.33 | with limited credit |
| Poe Plus | €27.36 | with limited credit |
| Krea Pro | ≈ €37.11 | with limited credit |
| Magnific Premium+ | €42.84 | with limited credit |
| Adobe Firefly Pro Plus | €54.99 | with limited credit |
| Poe Pro | €68.41 | with limited credit |
| Magnific Business | €70.21 | with limited credit, for teams, per seat |
| Magnific Pro Starter | €104.72 | with limited credit |
| ElevenLabs Pro | ≈ €104.96 | with limited credit |
| Krea Max | ≈ €111.32 | with limited credit |
| Poe Advanced | €136.84 | with limited credit |
| Krea Business | ≈ €212.05 | with limited credit, for teams |
| Adobe Firefly Premium | €219.98 | with limited credit |
| Magnific Pro | €273.70 | with limited credit |
| ElevenLabs Scale | ≈ €317.01 | with limited credit, for teams |
| Poe Max | €342.11 | with limited credit |
| ElevenLabs Business | ≈ €1,049.63 | with limited credit, for teams |
| Adobe Firefly Premium für Teams | n/a | with limited credit, for teams, per seat |
| Adobe Firefly Pro für Teams | n/a | with limited credit, for teams, per seat |
| Adobe Firefly Pro Plus für Teams | n/a | with limited credit, for teams, per seat |
| ElevenLabs Enterprise | n/a | for enterprises |
| Krea Enterprise | n/a | for enterprises |
| Magnific Enterprise | n/a | for enterprises |
Frequently asked questions about Runway Gen-4.5
How good is Runway Gen-4.5?
Rank 17 of 23 in the text-to-video arena rating.
LMArena, as of Sep 22, 2026
How much does a video with Runway Gen-4.5 cost?
About $0.60 for a 5 s clip, $0.12 per second of video. That is fairly cheap.
How long can a video with Runway Gen-4.5 be?
Up to 10 seconds in one go. Resolution: 720p.
According to Runway
- Price
- $0.12 per second$0.60 per 5 s clip
- Longest clip
- 10s
- Resolution
- 720p
- Open weights
- no
Where can I use Runway Gen-4.5?
At Runway with a subscription from ≈ €15.90 a month. Including other providers that makes 34 plans in Germany.
Subscription comparison, prices in Germany incl. VAT
At Runway
5 plans, from ≈ €15.90 a month (Runway Standard).
Through other providers
29 plans from 5 providers, from ≈ €6.36 a month (ElevenLabs Starter), with limited credits.
Sources and data date
Show all 27 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| LMArena | 0 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values. 1 measurements are not yet assigned to a test series.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 16, 2026. 23 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | arena-video-edit-exact-row Note The inspected Video Edit table has no exact model-version row. T2V and I2V values were not reused. |
| Not found in the inspected sources | vabench-exact-model-row Note VABench has no exact model row. Sora 2 was not transferred to Sora 2 Pro or other models. |
| Not found in the inspected sources | arena-i2v-exact-row Note No exact Arena image-to-video observation was found in the checked data. |
| Not found in the inspected sources | artificial-analysis-t2v-exact-row Note No exact model version or resolution was found in the inspected Artificial Analysis table. |
| Not found in the inspected sources | artificial-analysis-i2v-exact-row Note No exact model version or resolution was found in the inspected Artificial Analysis table. |
| Unresolved | vbench-current-public-leaderboard Note The current VBench leaderboard is embedded in a dynamic Hugging Face iframe and was not retrievable; current scores remain unresolved. |
| Not found in the inspected sources | vidbenchmark-exact-row Note No exact model id is present in the 2026-08-04 dataset; similarly named variants were not transferred. |
| Additional source | Runway · Runway Gen-4.5 creation guide · Editorial description reviewed October 2, 2026 |
| Additional source | Video pricing |
| Additional source | OpenRouter |
| Additional source | LMArena (retrieved November 5, 2026) |
| Additional source | VGI-Bench, arXiv:2608.19583v3 (retrieved October 16, 2026) |
| Additional source | Video Models by Wiro AI (retrieved October 16, 2026; October 28, 2026) |
| Additional source | BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios (retrieved October 17, 2026) |
| Additional source | VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects (retrieved October 17, 2026) |
| Additional source | CaliBench, Table 2 (retrieved October 17, 2026) |
| Additional source | VGI-Bench paper (retrieved October 17, 2026) |
| Additional source | Runway, official Gen-4.5 research announcement (retrieved October 18, 2026) |
| Additional source | SlopTV (retrieved October 22, 2026; October 28, 2026) |
| Additional source | SlopTV (retrieved October 24, 2026) |
| Additional source | Arena Video Text-to-Video (retrieved September 21, 2026; October 16, 2026; October 28, 2026) |
| Additional source | Model metadata (retrieved October 16, 2026)123 |
| Additional source | Model metadata (retrieved October 16, 2026; October 28, 2026) |
| Additional source | Model metadata (retrieved October 28, 2026)12 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |
| Additional source | Runway: Introducing Gen-4.5 (2026-09-19) |