How fast is OpenHands?

The median turn latency is 144.8 seconds per prompt, not per whole build, which derives to 21.7 min across the full nine prompt specification. That is a tenth percentile of 81.4 seconds and a ninetieth percentile of 269.1 seconds across 45 recorded executions.

How reliable is OpenHands?

64.4% of recorded executions met the published pass criterion with no operator intervention. 9 were partial and 7 failed outright. Every one of those rows is published on this page.

Coding agents / rank 15 of 17 / cycle 04

OpenHands benchmark

Open source and self hostable, and the only agent here whose sandbox runtime can be run entirely inside your own network. It is slower and less consistent than the commercial agents, and the spread reflects a sandbox that occasionally has to be rebuilt mid task. For anyone who cannot send a repository to a third party it is the strongest option in the index.

Last run: 15 Aug 2026 09:11 UTCNext scheduled run: n/aOfficial site OpenHands reviews and ratings

Composite index

63.93

of 100 | withheld vs. cycle 03

Delta not shown for cycle 04: the roster was re-based from one merged ranking into two class boards, so cycle 03 and cycle 04 ranks are not on the same scale. Resumes cycle 05.

At a glance

Composite index

63.93

rank 15 of 17

Rank

#15

of 17 on the coding agents board

Median turn latency

144.8 s per prompt

21.7 min across the full nine prompt spec, derived

Reliability

64.4%

strict pass rate

SEO score

56.0

0 to 100, SEO and GEO axis

Three strongest axes

Value86.0
Agent performance74.0
Scalability70.0

Three weakest axes

Turn latency score21.7
SEO and GEO56.0
Design output58.0

Median turn latency

144.8 s per prompt

p10 81.4 s, p90 269.1 s

Strict pass rate

64.4%

29 pass, 9 partial, 7 fail

Executions recorded

5 runs of 9 prompts

Entry price

No licence fee, self hosted

Vendor's own unit and billing period. Never a currency conversion

Per axis subscores

Composite recomputed from these 9 rows: 63.93. That is the arithmetic behind the index, and you can repeat it by hand. Rounding rule: half up at two decimals, applied uniformly to all 37 published products. Code ownership has no row here: it is not scored on this board.

Weight table

Per axis subscores against the roster median, and weighted contribution
Axis	Score	Median	Weight %	Contribution
Reliability	64.4	75.6	18.56	11.95
Agent performance	74.0	80.0	18.55	13.73
Scalability	70.0	74.0	13.4	9.38
SEO and GEO	56.0	56.0	12.37	6.93
API and MCP	68.0	70.0	9.28	6.31
Integrations	66.0	70.0	8.25	5.45
Design output	58.0	62.0	7.22	4.19
Turn latency score	21.7	39.9	7.22	1.57
Value	86.0	80.0	5.15	4.43

Turn latency distribution

Every recorded prompt duration for OpenHands, in seconds. Median wall clock time for one prompt, not for a whole build. The cyan tick on the whisker is the median.

min 62.8 smax 536.6 s

Spread against the cohort

p10 81.4 s / median 144.8 s / p90 269.1 s

Scale is shared with every product in the cohort, so the bars are directly comparable between pages. Ratio of p90 to median is 1.86x.

Outcome split

29 pass / 9 partial / 7 fail

SEO and GEO measurements

Taken from the public marketing page this product generated in prompt 8, fetched with JavaScript disabled.

SEO and GEO leaderboard

HTML bytes, no JS

18.0 KB

18,432 bytes of real text content with scripts blocked

LCP

1,980 ms

Throttled connection, cold cache

CLS

0.050

Cumulative layout shift on load

SEO and GEO subscore

56.0

0 to 100, worth 12.37 index points on this board

Raw run data: 45 executions

One row per prompt execution. Nothing is aggregated away, nothing is hidden, including the failures.

JSON

Raw per run measurements
Run	Prompt	Prompt target	Started	Duration (s)	Outcome	Note
R01	P01	Tenant and user model	11 Aug 2026 08:00 UTC	99.8	fail	Build did not start after deploy. Recorded as a fail with the log preserved.
R01	P02	Authentication and session	11 Aug 2026 08:03 UTC	144.8	pass
R01	P03	Projects CRUD with tenancy	11 Aug 2026 08:08 UTC	130.6	pass
R01	P04	Public REST API with keys	11 Aug 2026 08:12 UTC	90.7	pass
R01	P05	Outbound webhooks with signatures	11 Aug 2026 08:15 UTC	89.4	fail	Task abandoned by the agent with no artifact produced.
R01	P06	Background jobs	11 Aug 2026 08:19 UTC	146.5	pass
R01	P07	Admin panel	11 Aug 2026 08:23 UTC	403.4	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R01	P08	Public marketing surface	11 Aug 2026 08:32 UTC	183.0	pass
R01	P09	Hardening pass	11 Aug 2026 08:37 UTC	141.4	pass
R02	P01	Tenant and user model	12 Aug 2026 08:00 UTC	69.0	pass
R02	P02	Authentication and session	12 Aug 2026 08:03 UTC	138.8	pass
R02	P03	Projects CRUD with tenancy	12 Aug 2026 08:07 UTC	125.2	pass
R02	P04	Public REST API with keys	12 Aug 2026 08:11 UTC	257.4	pass
R02	P05	Outbound webhooks with signatures	12 Aug 2026 08:17 UTC	536.6	partial	Pagination off by one at the final page boundary.
R02	P06	Background jobs	12 Aug 2026 08:28 UTC	251.6	pass
R02	P07	Admin panel	12 Aug 2026 08:34 UTC	214.9	pass
R02	P08	Public marketing surface	12 Aug 2026 08:40 UTC	76.5	pass
R02	P09	Hardening pass	12 Aug 2026 08:43 UTC	126.4	partial	Error envelope inconsistent between two of the endpoints.
R03	P01	Tenant and user model	13 Aug 2026 08:00 UTC	147.9	pass
R03	P02	Authentication and session	13 Aug 2026 08:04 UTC	66.4	pass
R03	P03	Projects CRUD with tenancy	13 Aug 2026 08:07 UTC	88.7	pass
R03	P04	Public REST API with keys	13 Aug 2026 08:11 UTC	62.8	pass
R03	P05	Outbound webhooks with signatures	13 Aug 2026 08:14 UTC	242.1	pass
R03	P06	Background jobs	13 Aug 2026 08:20 UTC	120.5	partial	Required one clarifying instruction before the criterion was met.
R03	P07	Admin panel	13 Aug 2026 08:24 UTC	159.7	pass
R03	P08	Public marketing surface	13 Aug 2026 08:28 UTC	295.3	pass
R03	P09	Hardening pass	13 Aug 2026 08:35 UTC	99.9	fail	Generated migration conflicted with the existing schema and was not reconciled.
R04	P01	Tenant and user model	14 Aug 2026 08:00 UTC	88.9	pass
R04	P02	Authentication and session	14 Aug 2026 08:03 UTC	196.4	partial	Pagination off by one at the final page boundary.
R04	P03	Projects CRUD with tenancy	14 Aug 2026 08:08 UTC	75.3	pass
R04	P04	Public REST API with keys	14 Aug 2026 08:12 UTC	216.4	fail	Task abandoned by the agent with no artifact produced.
R04	P05	Outbound webhooks with signatures	14 Aug 2026 08:17 UTC	115.3	partial	Required one clarifying instruction before the criterion was met.
R04	P06	Background jobs	14 Aug 2026 08:21 UTC	188.9	fail	Generated migration conflicted with the existing schema and was not reconciled.
R04	P07	Admin panel	14 Aug 2026 08:26 UTC	256.1	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R04	P08	Public marketing surface	14 Aug 2026 08:32 UTC	149.0	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R04	P09	Hardening pass	14 Aug 2026 08:37 UTC	125.3	pass
R05	P01	Tenant and user model	15 Aug 2026 08:00 UTC	216.3	pass
R05	P02	Authentication and session	15 Aug 2026 08:05 UTC	264.3	fail	Task abandoned by the agent with no artifact produced.
R05	P03	Projects CRUD with tenancy	15 Aug 2026 08:12 UTC	288.0	pass
R05	P04	Public REST API with keys	15 Aug 2026 08:18 UTC	168.3	partial	Delivered the main path, missed the boundary case named in the pass criteria.
R05	P05	Outbound webhooks with signatures	15 Aug 2026 08:23 UTC	215.2	pass
R05	P06	Background jobs	15 Aug 2026 08:29 UTC	94.3	fail	Generated migration conflicted with the existing schema and was not reconciled.
R05	P07	Admin panel	15 Aug 2026 08:32 UTC	116.5	pass
R05	P08	Public marketing surface	15 Aug 2026 08:36 UTC	131.6	pass
R05	P09	Hardening pass	15 Aug 2026 08:40 UTC	272.3	pass

Pricing

Free and open source, self hosted. A managed cloud option is metered. You supply the model key either way.

Entry price: No licence fee, self hosted
Priced from: vendor pricing page
Value subscore: 86.0
Index points per euro: No licence fee

Entry price is the vendor's own published figure, fetched 21 Aug 2026, never a currency conversion. The currency label is the vendor's own except where the pricing note above records that this lab inferred it. Index points per euro is computed from a separate, euro-normalised figure used only for the Value axis: Converted at the European Central Bank euro reference rate of 1.1699 US dollars to the euro, August 21, 2026.

Capabilities as measured

stack: Your repository, any framework
deploy: Self hosted runtime
database: Whatever you already run
auth: It wires the library you choose
background jobs: Implemented in your stack
webhooks: Written, signing on request
rest api: Written to your conventions
mcp server: Yes
export code: Fully open source, nothing leaves your network
custom domain: Your hosting decides
ssr: Your framework decides

Screenshot

OpenHands landing page, captured by the lab on 14 Aug 2026 at 1440 by 900. Stored locally, never hotlinked.

OpenHands landing page, captured by the lab at 1440 by 900

OpenHands, captured 14 Aug 2026.

Sources and fetch dates

Every claim on this page traces to one of these.

Sources with fetch dates
Source	URL	Fetched
OpenHands pricing page	https://openhands.dev/pricing	14 Aug 2026
OpenHands product site	https://openhands.dev	14 Aug 2026
LLM Tier run harness output	https://www.llm-tier.com/api/runs.json	14 Aug 2026

Rich results carry this composite as 3.2 on a 0 to 5 scale because that is the only scale the format accepts. The number on this page, 0 to 100, is the real one.

Reader index

Voted by readers with an account, one score per person per axis. Published beside the lab index, never inside it.

Score it or read the notes

Reader index

not rated yet

Lab index

63.93

2 readers have scored 100% of the index weight so far. A reader index is published at 3 voters and 50% coverage.

Seeded at launch

The reader scores, lab notes and open ratings published here were written by this lab in August 2026 to populate the reader column before the site had readers. They are not customer submissions, they are not vendor supplied and nobody was paid for them. Anything submitted since then comes from a registered account. The lab index is measured from logged runs and is unaffected either way.

Reader mean against the measured lab subscore for each axis
Axis	Weight	Lab	Readers	Votes
Agent performance	18.55%	74.0	74.0	2
Reliability	18.56%	64.4	66.5	2
Scalability	13.4%	70.0	69.0	1
SEO and GEO	12.37%	56.0	56.0	2
API and MCP	9.28%	68.0	75.0	2
Integrations	8.25%	66.0	69.5	2
Design output	7.22%	58.0	56.5	2
Turn latency score	7.22%	21.7	25.0	2
Value	5.15%	86.0	90.0	2

The reader index is a weighted mean of reader submitted axis scores using the published index weights, renormalised over the axes readers have scored. It is never blended into the lab index. How this works.

Open rating mean

n/a

0 published open ratings, submitted without an account

Lab index

63.93

Measured, not voted

Gap to the measurement

n/a

Positive means open raters put it above the measurement

What agent performance looked like in practice

Across 45 recorded executions this product met the published pass criterion cleanly 29 times, partially 9 times and failed 7 times. The rows above carry the reviewer note for every non clean outcome, which is the only way to tell a product that fails loudly from one that fails quietly.