Xiaomi: MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attentio…

xiaomi/mimo-v2.6-flash-20260921

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.

Specifications & capabilities

Input
text, image, video, audio
Output
text
Context window · tokens
1050000
Published model ID
mimo-v2.6-flash
Capabilities
audioInput, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Description source ↗

Evaluations

21–26 / 26

OpenRouter Benchmarks

85.211%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Venice
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
14
sample size
364
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Venice
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-17T08:17:58.236Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
364
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8521062280219781
accuracy_std_dev
0.006055500000000047
cost_per_task_usd
0.005501717032967033
output_tokens_per_task
15491.851648351649
latency_seconds_per_task
539.158467032967
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
39
benchmark_evaluation
true
openrouter_permaslug
xiaomi/mimo-v2.6-flash-20260921
source model id
xiaomi/mimo-v2.6-flash-20260921
Original result ↗

OpenRouter Benchmarks

77.525%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · GMICloud
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
22
sample size
1188
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
GMICloud
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T09:00:40.586Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1188
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7752525
accuracy_std_dev
0.02576620138055538
cost_per_task_usd
0.011368148148148148
output_tokens_per_task
43361.55303030303
latency_seconds_per_task
910.0711422558923
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
26
benchmark_evaluation
true
openrouter_permaslug
xiaomi/mimo-v2.6-flash-20260921
source model id
xiaomi/mimo-v2.6-flash-20260921
Original result ↗

OpenRouter Benchmarks

77.415%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · DeepInfra
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
37
sample size
1180
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
7
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
DeepInfra
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:17:43.227Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1180
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7741524627118646
accuracy_std_dev
0.024920321732780762
cost_per_task_usd
0.010626239830508475
output_tokens_per_task
40411.0593220339
latency_seconds_per_task
1250.0368076271186
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
71
benchmark_evaluation
true
openrouter_permaslug
xiaomi/mimo-v2.6-flash-20260921
source model id
xiaomi/mimo-v2.6-flash-20260921
Original result ↗

OpenRouter Benchmarks

75.635%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Novita
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
37
sample size
1182
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Novita
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:41:02.325Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1182
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.7563452081218275
accuracy_std_dev
0.0358022938821275
cost_per_task_usd
0.014391308798646361
output_tokens_per_task
51071.41201353638
latency_seconds_per_task
1040.5566945854484
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
59
benchmark_evaluation
true
openrouter_permaslug
xiaomi/mimo-v2.6-flash-20260921
source model id
xiaomi/mimo-v2.6-flash-20260921
Original result ↗

OpenRouter Benchmarks

73.216%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
95
sample size
990
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
5
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T08:31:11.846Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
990
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.732155
accuracy_std_dev
0.02424727451075689
cost_per_task_usd
0.016461675757575758
output_tokens_per_task
60883.92525252525
latency_seconds_per_task
673.2722666666667
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
132
benchmark_evaluation
true
openrouter_permaslug
xiaomi/mimo-v2.6-flash-20260921
source model id
xiaomi/mimo-v2.6-flash-20260921
Original result ↗

Published prices

1–20 / 35

xiaomi/mimo-v2.6-flash ↗

$0.0028

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

xiaomi/mimo-v2.6-flash ↗

$0.14

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

xiaomi/mimo-v2.6-flash ↗

$0.28

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

xiaomi/mimo-v2.6-flash ↗

$0.0028

Inference provider
vercelAIGatewayCatalog
Platform
boundless
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
boundless | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
boundless
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
boundless | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.28

Inference provider
vercelAIGatewayCatalog
Platform
boundless
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
boundless | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.0028

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | xiaomi/mimo-v2.6-flash
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | xiaomi/mimo-v2.6-flash
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.28

Inference provider
vercelAIGatewayCatalog
Platform
deepinfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
deepinfra | xiaomi/mimo-v2.6-flash
model_type
language
quantization
fp8
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.0024

Inference provider
vercelAIGatewayCatalog
Platform
gmicloud
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
gmicloud | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.11

Inference provider
vercelAIGatewayCatalog
Platform
gmicloud
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
gmicloud | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.22

Inference provider
vercelAIGatewayCatalog
Platform
gmicloud
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
gmicloud | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.0028

Inference provider
vercelAIGatewayCatalog
Platform
inference-net
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
inference-net | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
inference-net
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
inference-net | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.28

Inference provider
vercelAIGatewayCatalog
Platform
inference-net
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
inference-net | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.0028

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.28

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.0028

Inference provider
vercelAIGatewayCatalog
Platform
tencent
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
tencent | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

xiaomi/mimo-v2.6-flash ↗

$0.14

Inference provider
vercelAIGatewayCatalog
Platform
tencent
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
tencent | xiaomi/mimo-v2.6-flash
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–2 / 2

Xiaomi: mimo-v2.6-flash ↗

source model id
mimo-v2.6-flash
hosting
mimo-hosted
platforms
  • Xiaomi MiMo
context length
1048576
max output tokens
131072
architecture
modality
any->text
tokenizer
Byte-Level Byte-Pair Encoding (BBPE)
quantization
FP8
input_modalities
  • text
  • image
  • video
  • audio
output_modalities
  • text
capabilities
  • streaming
  • reasoning
  • toolCalling
  • structuredOutputs
  • promptCaching

MiMo V2.6 Flash ↗

source model id
xiaomi/mimo-v2.6-flash
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1048576
max output tokens
131072
architecture
input_modalities
  • text
  • audio
  • image
  • video
output_modalities
  • text
capabilities
  • audioInput
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput

Source specification observations

1–6 / 6

openRouter ↗

field
context_length
value
1050000
normalized value
1050000
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

xiaomiMiMo ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
xiaomiMiMo
confidence
1

openRouter ↗

field
max_output_tokens
value
131072
normalized value
131072
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
131072
normalized value
131072
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

xiaomiMiMo ↗

field
max_output_tokens
value
131072
normalized value
131072
scope
source-model
source id
xiaomiMiMo
confidence
1

Original sources

1–8 / 8

Hugging Face · XiaomiMiMo/MiMo-V2.6-Flash-RL ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

Xiaomi MiMo · Source snapshot ↗

OpenRouter · Catalog ↗

OpenRouter · Catalog ↗

Vercel AI Gateway · Catalog ↗

Xiaomi MiMo · Catalog ↗

Source links

1–6 / 6

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace